Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns
In this study, we present the EEG-GCN, a novel hybrid model for the prediction of time series data, adept at address ing the inherent challenges posed by the data’s complex, non-linear, and periodic nature, as well as the noise that fre quently accompanies it. This model synergizes signal decomposit...
- Autores:
-
Han, Huimin
Neira Molin, Harold
Khan, Asad
Fang, Meie
Mahmoud, Haitham A.
Mahrous Awwad, Emad
Ahmed, Bilal
Yasin Ghadi, Yazeed
- Tipo de recurso:
- Article of journal
- Fecha de publicación:
- 2024
- Institución:
- Corporación Universidad de la Costa
- Repositorio:
- REDICUC - Repositorio CUC
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.cuc.edu.co:11323/10681
- Acceso en línea:
- https://hdl.handle.net/11323/10681
https://repositorio.cuc.edu.co
- Palabra clave:
- Time series forecasting
EEMD
CEEMDAN
GCN
- Rights
- openAccess
- License
- Atribución 4.0 Internacional (CC BY 4.0)
| id |
RCUC2_dc137f59591f45dfab64366016e2ac57 |
|---|---|
| oai_identifier_str |
oai:repositorio.cuc.edu.co:11323/10681 |
| network_acronym_str |
RCUC2 |
| network_name_str |
REDICUC - Repositorio CUC |
| repository_id_str |
|
| dc.title.eng.fl_str_mv |
Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns |
| title |
Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns |
| spellingShingle |
Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns Time series forecasting EEMD CEEMDAN GCN |
| title_short |
Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns |
| title_full |
Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns |
| title_fullStr |
Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns |
| title_full_unstemmed |
Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns |
| title_sort |
Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns |
| dc.creator.fl_str_mv |
Han, Huimin Neira Molin, Harold Khan, Asad Fang, Meie Mahmoud, Haitham A. Mahrous Awwad, Emad Ahmed, Bilal Yasin Ghadi, Yazeed |
| dc.contributor.author.none.fl_str_mv |
Han, Huimin Neira Molin, Harold Khan, Asad Fang, Meie Mahmoud, Haitham A. Mahrous Awwad, Emad Ahmed, Bilal Yasin Ghadi, Yazeed |
| dc.subject.proposal.eng.fl_str_mv |
Time series forecasting EEMD CEEMDAN GCN |
| topic |
Time series forecasting EEMD CEEMDAN GCN |
| description |
In this study, we present the EEG-GCN, a novel hybrid model for the prediction of time series data, adept at address ing the inherent challenges posed by the data’s complex, non-linear, and periodic nature, as well as the noise that fre quently accompanies it. This model synergizes signal decomposition techniques with a graph convolutional neural network (GCN) for enhanced analytical precision. The EEG-GCN approaches time series data as a one-dimensional temporal signal, applying a dual-layered signal decomposition using both Ensemble Empirical Mode Decomposi tion (EEMD) and GRU. This two-pronged decomposition process efectively eliminates noise interference and distills the complex signal into more tractable sub-signals. These sub-signals facilitate a more straightforward feature analysis and learning process. To capitalize on the decomposed data, a graph convolutional neural network (GCN) is employed to discern the intricate feature interplay within the sub-signals and to map the interdependencies among the data points. The predictive model then synthesizes the weighted outputs of the GCN to yield the fnal forecast. A key component of our approach is the integration of a Gated Recurrent Unit (GRU) with EEMD within the GCN framework, referred to as EEMD-GRU-GCN. This combination leverages the strengths of GRU in capturing temporal dependencies and the EEMD’s capability in handling non-stationary data, thereby enriching the feature set available for the GCN and enhancing the overall predictive accuracy and stability of the model. Empirical evaluations demonstrate that the EEG-GCN model achieves superior performance metrics. Compared to the baseline GCN model, EEG-GCN shows an average R2 improvement of 60% to 90%, outperforming the other methods. These results substantiate the advanced predictive capability of our proposed model, underscoring its potential for robust and accurate time series forecasting. |
| publishDate |
2024 |
| dc.date.accessioned.none.fl_str_mv |
2024-01-31T21:46:46Z |
| dc.date.available.none.fl_str_mv |
2024-01-31T21:46:46Z |
| dc.date.issued.none.fl_str_mv |
2024-01-18 |
| dc.type.spa.fl_str_mv |
Artículo de revista |
| dc.type.coar.fl_str_mv |
http://purl.org/coar/resource_type/c_2df8fbb1 |
| dc.type.coar.spa.fl_str_mv |
http://purl.org/coar/resource_type/c_6501 |
| dc.type.content.spa.fl_str_mv |
Text |
| dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/article |
| dc.type.redcol.spa.fl_str_mv |
http://purl.org/redcol/resource_type/ART |
| dc.type.version.spa.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
| dc.type.coarversion.spa.fl_str_mv |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| format |
http://purl.org/coar/resource_type/c_6501 |
| status_str |
publishedVersion |
| dc.identifier.citation.spa.fl_str_mv |
Han, H., Neira-Molin, H., Khan, A. et al. Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns. J Cloud Comp 13, 20 (2024). https://doi.org/10.1186/s13677-023-00560-1 |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/11323/10681 |
| dc.identifier.doi.none.fl_str_mv |
10.1186/s13677-023-00560-1 |
| dc.identifier.eissn.spa.fl_str_mv |
2192-113X |
| dc.identifier.instname.spa.fl_str_mv |
Corporación Universidad de la Costa |
| dc.identifier.reponame.spa.fl_str_mv |
REDICUC - Repositorio CUC |
| dc.identifier.repourl.spa.fl_str_mv |
https://repositorio.cuc.edu.co |
| identifier_str_mv |
Han, H., Neira-Molin, H., Khan, A. et al. Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns. J Cloud Comp 13, 20 (2024). https://doi.org/10.1186/s13677-023-00560-1 10.1186/s13677-023-00560-1 2192-113X Corporación Universidad de la Costa REDICUC - Repositorio CUC |
| url |
https://hdl.handle.net/11323/10681 https://repositorio.cuc.edu.co |
| dc.language.iso.spa.fl_str_mv |
eng |
| language |
eng |
| dc.relation.ispartofjournal.spa.fl_str_mv |
Journal of Cloud Computing |
| dc.relation.references.spa.fl_str_mv |
1. Salles R, Pacitti E, Bezerra E, Porto F, Ogasawara E (2022) T S Pred: a framework for nonstationary time series prediction. Neurocomputing 467:197–202 2. Goudarzi G, Birgani YT, Assarehzadegan MA, Neisi A, Dastoorpoor M, Sorooshian A, Yazdani M (2022) Prediction of airborne pollen concentra tions by artifcial neural network and their relationship with meteorologi cal parameters and air pollutants. J Environ Health Sci Eng 20(1):251–264 3. Méndez M, Merayo MG, Núñez M (2023) Long-term trafc fow forecast ing using a hybrid CNN-BiLSTM model. Eng Appl Artif Intell 121:106041 4. Bhatti U, Masud M, Bazai S, Tang H (2023). Editorial: Investigating AI-based smart precision agriculture techniques. Front Plant Sci 14 https://doi.org/ 10.3389/fpls.2023.1237783. 5. Fischer E, Barreca G, Greco A et al (2023) Seismic risk assessment of a large metropolitan area by means of simulated earthquakes. Nat Hazards 118:117–153 6. Mahmoud A, Mohammed A (2021) A survey on deep learning for timeseries forecasting. In: Hassanien AE, Darwish A. (eds) Machine learning and big data analytics paradigms: analysis, applications and challenges. Studies in Big Data. vol 77. Springer, Cham. 7. Guo K, Yu X, Liu G, Tang S (2023) A Long-Term Trafc Flow Prediction Model Based on Variational Mode Decomposition and Auto-Correlation Mechanism. Appl Sci 13:7139 8. Hahn Y, Langer T, Meyes R, Meisen T (2023) Time Series Dataset Survey for Forecasting with Deep Learning. Forecasting 5:315–335 9. Ning Y, Kazemi H, Tahmasebi P (2022) A comparative machine learning study for time series oil production forecasting: ARIMA, LSTM, and Prophet. Comput Geosci 164:105126 10. Dong S, Xiao J, Xiaolin Hu, Fang N, Liu L, Yao J (2023) Deep transfer learn ing based on Bi-LSTM and attention for remaining useful life prediction of rolling bearing. Reliab Eng Syst Saf 230:108914 11. He R, Zhang C, Xiao Y, Lu X, Zhang S, Yanbing Liu Y (2024) Deep spatiotemporal 3D dilated dense neural network for trafc fow prediction. Expert Syst Appl 237(Part A):121394. 12. Yuan Y, Shao C, Cao Z, Chen W, Yin A, Yue H, Xie B (2019) Urban rail transit passenger fow forecasting method based on the coupling of artifcial fsh swarm and improved particle swarm optimization algorithms. Sus tainability 11:7230 13. Zheng H, Chen J, Huang Z, Yang K, Zhu J (2022) Short-Term Online Fore casting for Passenger Origin-Destination (OD) Flows of urban rail transit: a graph-temporal fused deep learning method. Mathematics 10:3664 14. Banerjee N, Morton A, Akartunal K (2020) Passenger demand forecasting in scheduled transportation. Eur J Oper Res 286(3):797–810 15. Li W, Sui L, Zhou M et al (2021) Short-term passenger fow forecast for urban rail transit based on multi-source data. J Wireless Com Network 2021:9 16. Toan TD, Truong V-H (2021) Support vector machine for short-term trafc fow prediction and improvement of its model training using nearest neighbor approach. Transp Res Rec 2675(4):362–373 17. Liu Y, Rasouli S, Wong M, Feng T, Huang T (2024) RT-GCN: Gaussian-based spatiotemporal graph convolutional network for robust trafc prediction. Inform Fusion 102:102078 18. Luo X, Li D, Zhang S (2019) Trafc Flow Prediction during the Holidays Based on DFT and SVR. Journal of Sensors 2019:1–10. https://doi.org/10. 1155/2019/6461450 19. Ma C, Zhao Y, Dai G, Xu X, Wong SC (2022). A novel STFSA-CNN-GRU Hybrid model for short-term trafc speed prediction. IEEE Transact Intell Transport Systems. PP. 1–10. https://doi.org/10.1109/TITS.2021.3117835. 20. Wang S, Shao C, Zhang J, Zheng Y, Meng M (2022) Trafc fow prediction using bi-directional gated recurrent unit method. Urban Inform 1(1):16 21. Zafar N, Haq IU, Chughtai JU, Shafq O (2022) Applying Hybrid Lstm-Gru Model Based on Heterogeneous Data Sources for Trafc Speed Prediction in Urban Areas. Sensors (Basel) 22(9):3348 22. Zhang W, Yao R, Du X, Ye J. (2021). Hybrid deep spatio-temporal models for trafc fow prediction on holidays and under adverse weather. IEEE Access. PP. 1–1. https://doi.org/10.1109/ACCESS.2021.3127584. 23. Bhatti UA, Huang M, Neira-Molina H, Marjan S, Baryalai M, Tang H, Wu G, Bazai SU (2023) MFFCG – Multi feature fusion for hyperspectral image classifcation using graph attention network. Expert Syst Appl 229 (Part A):120496 24. Fodstad M, del Granado PC, Hellemo L, Knudsen BR, Pisciella P, Silvast A, Bordin C, Schmidt S, Straus J (2022) Next frontiers in energy system modelling: a review on challenges and the state of the art. Renew Sustain Energy Rev 160:112246. 25. Joe P, Sun J, Yussouf N, Goodman S, Riemer M, Gouda KC, Golding B, Rogers R, Isaac G, Wilson J, Li PW, Wulfmeyer V, Elmore K, Onvlee J, Chong P and Ladue J (2022) Predicting the weather: a partnership of observa tion scientists and forecasters. In: Golding, B. (eds) Towards the “Perfect” Weather Warning. Springer, Cham. 26. Yan J, Möhrlen C, Göçmen T, Kelly M, Wessel A, Giebel G (2022) Uncover ing wind power forecasting uncertainty sources and their propaga tion through the whole modelling chain. Renew Sustain Energy Rev 165:112519 27. Wang H (2023) Extreme learning Kalman flter for short-term wind speed prediction. Front Energy Res 10:1047381. https://doi.org/10.3389/fenrg. 2022.1047381 28. Fattah J, Ezzine L, Aman Z, El Moussami H, Lachhab A 2018 Forecasting of demand using ARIMA model. Int J Eng Bus Manag 10. 29. Hanif S, Lotfan S, Zare-Behtash H, Cammarano A (2022) Ofshore wind power forecasting—A new hyperparameter optimisation algorithm for deep learning models. Energies 15:6919 30. Ospina R, Gondim JAM, Leiva V, Castro C (2023) An overview of forecast analysis with ARIMA Models during the COVID-19 Pandemic: methodol ogy and case study in Brazil. Mathematics 11:3069 31. Wang S, Wang J, Haiyan Lu, Zhao W (2021) A novel combined model for wind speed prediction – Combination of linear model, shallow neural networks, and deep learning approaches. Energy 234:121275 32. Nair KR, Vanitha V and Jisma M (2017) Forecasting of wind speed using ANN, ARIMA and Hybrid models, 2017 International Conference on Intel ligent Computing, Instrumentation and Control Technologies (ICICICT), Kerala, India, 2017, pp. 170–175, 33. Liu H, Tian H-q, Li Y-F (2012) Comparison of two new ARIMA-ANN and ARIMA-Kalman hybrid methods for wind speed prediction. Appl Energy 98:415–424 34. Aasim SN, Singh AM (2019) Repeated wavelet transform based ARIMA model for very short-term wind speed forecasting. Renew Energy 136:758–768. 35. Bhatti UA, Hashmi MZ, Sun Y, Masud M, Nizamani MM (2023) Editorial: Artifcial intelligence applications in reduction of carbon emissions: Step towards sustainable environment. Front Environ Sci 11:1183620 36. Zhang X, Wu X, Zhu G, Lu X, Wang K (2022) A seasonal ARIMA model based on the gravitational search algorithm (GSA) for runof prediction. Water Supply 22(8): 6959–6977. 37. Wang H, Yan S, Ju D, Ma N, Fang J, Wang S, Li H, Zhang T, Xie Y, Wang J (2023) Short-term photovoltaic power forecasting based on a feature rise-dimensional two-layer ensemble learning model. Sustainability 15:15594 38. Shuai Hu, Xiang Y, Zhang H, Xie S, Li J, Chenghong Gu, Sun W, Liu J (2021) Hybrid forecasting method for wind power integrating spatial correlation and corrected numerical weather prediction. Appl Energy 293:116951 39. Nawab F, Abd Hamid AS, Ibrahim A, Sopian K, Fazlizan A, Fauzan MF (2023) Solar irradiation prediction using empirical and artifcial intel ligence methods: a comparative review. Heliyon 9(6) 40. Deng Y, Zhou X, Shen J, Xiao G, Hong H, Lin H, Wu F, Liao BQ (2021) New methods based on back propagation (BP) and radial basis function (RBF) artifcial neural networks (ANNs) for predicting the occurrence of halok etones in tap water. Sci Total Environ 10(772):145534 41. Ellahi M, Usman MR, Arif W, Usman HF, Khan WA, Satrya GB, Daniel K, Shabbir N (2022) Forecasting of wind speed and power through FFNN and CFNN using HPSOBA and MHPSO-BAACs techniques. Electronics 11:4193 42. Chen N, Xiong C, Du W, Wang C, Lin X, Chen Z (2019) An Improved Genetic Algorithm Coupling a Back-Propagation Neural Network model (IGA-BPNN) for water-level predictions. Water 11:1795 43. Bhatti UA, Tang H, Wu G, Marjan S, Hussain A (2023) Deep learning with graph convolutional networks: an overview and latest applications in computational intelligence. Int J Intell Syst 2023:1–28 44. Al-Majidi SD, Abbod MF, Al-Raweshidy HS (2020) A particle swarm optimi sation-trained feedforward neural network for predicting the maximum power point of a photovoltaic array. Eng Appl Artif Intell 92:103688 45. Husein M, Chung IY. Day-ahead solar irradiance forecasting for microgrids using a long short-term memory recurrent neural network: A deep learn ing approach. Energies. 2019;12(10):1856. 46. Uncuoglu E, Citakoglu H, Latifoglu L, Bayram S, Laman M, Mucella Ilkentapar, Alper Oner AA (2022) Comparison of neural network, Gaussian regression, support vector machine, long short-term memory, multigene genetic programming, and M5 Trees methods for solving civil engineering problems. Appl Soft Comput 129:109623 47. Zhang C, Zhang M (2022) Wavelet-based neural network with genetic algorithm optimization for generation prediction of PV plants. Energy Rep 8:10976–10990 48. Park R-J, Song K-B, Kwon B-S (2020) Short-term load forecasting algorithm using a similar day selection method based on reinforcement learning. Energies 13:2640 49. Bhatti U, Bazai S, Hussain S, Fakhar S, Ku C, Marjan S, Por Y, Jing L (2023). Deep learning-based trees disease recognition and classifcation using hyperspectral data. Compu Mat Continua 77:681–697. https://doi.org/10. 32604/cmc.2023.037958. 50. Gagnon P, Cole W (2022) Planning for the evolution of the electric grid with a long-run marginal emission rate. iScience 25(3):103915. 51. Almani AA, Han X (2023) Real-time pricing-enabled demand response using long short-time memory deep learning. Energies 16:2410 52. Barton M, Lennox B (2022) Model stacking to improve prediction and variable importance robustness for soft sensor development. Digital Chem Eng 3 53. Zheng H, Yuan J, Chen L (2017) Short-term load forecasting using emdlstm neural networks with a Xgboost algorithm for feature importance evaluation. Energies 10:1168 54. Vanting NB, Ma Z, Jørgensen BN (2021) A scoping review of deep neural networks for electric load forecasting. Energy Inform 4(Suppl 2):49 55. Xu Y, Liu X, Cao X, Huang C, Liu E, Qian S, Liu X, Yanjun Wu, Dong F, Qiu C-W, Qiu J, Hua K, Wentao Su, Jian Wu, Huiyu Xu, Han Y, Chenguang Fu, Yin Z, Liu M, Roepman R, Dietmann S, Virta M, Kengara F, Zhang Ze, Zhang L, Zhao T, Dai Ji, Yang J, Lan L, Luo M, Liu Z, An T, Zhang B, He X, Cong S, Liu X, Zhang W, Lewis JP, Tiedje JM, Wang Qi, An Z, Wang F, Zhang L, Huang T, Chuan Lu, Cai Z, Wang F, Zhang J (2021) Artifcial intelligence: a powerful paradigm for scientifc research. Innovation 2(4):100179 56. Ullah I, Muhammad Hasanat S, Aurangzeb K, Alhussein M, Rizwan M, Anwar MS (2023) Multi-horizon short-term load forecasting using hybrid of LSTM and modifed split convolution. PeerJ Comput Sci 15(9):e1487 57. Muhammad Ahsan Zamee, Dongjun Han, Heejune Cha, Dongjun Won (2023) Self-supervised online learning algorithm for electric vehicle charging station demand and event prediction. J Energy Storage 71:108189. 58. Zheng J, Zhu J, Xi H (2023) Short-term energy consumption prediction of electric vehicle charging station using attentional feature engineering and multi-sequence stacked Gated Recurrent Unit. Comput Electr Eng 108:108694 59. He W, Li Z, Liu T, Liu Z, Guo X, Jinguang Du, Li X, Sun P, Ming W (2023) Research progress and application of deep learning in remaining useful life, state of health and battery thermal management of lithium batteries. J Energy Storage 70:107868 60. Bhatia K, Mittal R, Varanasi J, Tripathi MM (2021) An ensemble approach for electricity price forecasting in markets with renewable energy resources. Utilities Policy 70:101185. 61. Xinxin W, Xiaopan S, Xueyi A, Shijia L (2023) Short-term wind speed fore casting based on a hybrid model of ICEEMDAN, MFE, LSTM and informer. PLoS One 18(9):e0289161 62. Zhao L, Li Z, Zhang J, Teng B (2023) An integrated complete ensemble empirical mode decomposition with adaptive noise to optimize LSTM for signifcant wave height forecasting. J Mar Sci Eng 11:435 63. Liu H, Xiong X, Yang B, Cheng Z, Shao K, Tolba A (2023) A power load fore casting method based on intelligent data analysis. Electronics 12:3441 64. Nepal B, Yamaha M, Yokoe A, Yamaji T (2020) Electricity load forecasting using clustering and ARIMA model for energy management in buildings. Jpn Archit Rev 3:62–76 65. Saglam M, Spataru C, Karaman OA (2023) Forecasting electricity demand in Turkey using optimization and machine learning algorithms. Energies 16:4499 66. Henrique BM, Sobreiro VA, Kimura H (2018) Stock price prediction using support vector regression on daily and up to the minute prices. J Finance Data Sci 4(3):183–201. 67. Gupta D, Pratama M, Ma Z, Li J, Prasad M (2019) Financial time series forecasting using twin support vector regression. PLoS One 14(3) 68. Ashfaq T and Javaid N (2019) "Short-term electricity load and price fore casting using enhanced KNN," 2019 International Conference on Frontiers of Information Technology (FIT), Islamabad, Pakistan, pp. 266–2665. 69. Maleki H, Sorooshian A, Goudarzi G, Baboli Z, Birgani YT, Rahmati M (2019) Air pollution prediction by using an artifcial neural network model. Clean Technol Environ Policy 21(6):1341–1352 70. Sarker IH (2021) Deep Learning: a comprehensive overview on tech niques, taxonomy, applications and research directions. Sn Comput Sci 2:420 71. Zha W, Liu Y, Wan Y, Luo R, Li D, Yang S, Yanmei Xu (2022) Forecasting monthly gas feld production based on the CNN-LSTM model. Energy 260:124889 72. Zhang Q, Jin Q, Chang J, et al (2018) Kernel-weighted graph convolu tional network: a deep learning approach for trafc forecasting[C]//2018 24th International Conference on Pattern Recognition (ICPR). IEEE 1018–1023. 73. Yin H, Zuhong Ou, Huang S, Meng A (2019) A cascaded deep learning wind power prediction approach based on a two-layer of mode decom position. Energy 189:116316 74. Zhang J, Siya W, Zhongfu T, Anli S (2023) An improved hybrid model for short term power load prediction. Energy 268:126561 75. Shu W, Gao Q (2020) Forecasting stock price based on frequency compo nents by EMD and neural networks. Ieee Access 8:206388–206395 76. Wu YX, Wu QB, Zhu JQ (2019) Improved EEMD-based crude oil price forecasting using LSTM networks. Physica A 516:114–124 77. Yin C, Wang G, Liao J (2023) Application of VMD–SSA–BiLSTM algorithm to smart grid fnancial market time series forecasting and sustainable innovation management. Front Energy Res 11:1239542 |
| dc.relation.citationendpage.spa.fl_str_mv |
1 |
| dc.relation.citationissue.spa.fl_str_mv |
20 |
| dc.relation.citationvolume.spa.fl_str_mv |
13 |
| dc.relation.citationedition.spa.fl_str_mv |
19 |
| dc.rights.license.spa.fl_str_mv |
Atribución 4.0 Internacional (CC BY 4.0) |
| dc.rights.uri.spa.fl_str_mv |
https://creativecommons.org/licenses/by/4.0/ |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.coar.spa.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| rights_invalid_str_mv |
Atribución 4.0 Internacional (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/ http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.spa.fl_str_mv |
19 páginas |
| dc.format.mimetype.spa.fl_str_mv |
application/pdf |
| dc.publisher.spa.fl_str_mv |
Springer Science + Business Media |
| dc.publisher.place.spa.fl_str_mv |
United States |
| dc.source.spa.fl_str_mv |
https://journalofcloudcomputing.springeropen.com/articles/10.1186/s13677-023-00560-1 |
| institution |
Corporación Universidad de la Costa |
| bitstream.url.fl_str_mv |
https://repositorio.cuc.edu.co/bitstream/11323/10681/1/Advanced%20series%20decomposition%20with%20a%20gated%20recurrent%20unit%20and%20graph%20convolutional%20neural%20network%20for%20non-stationary%20data%20patterns-2024-01-18.pdf https://repositorio.cuc.edu.co/bitstream/11323/10681/2/license.txt https://repositorio.cuc.edu.co/bitstream/11323/10681/3/Advanced%20series%20decomposition%20with%20a%20gated%20recurrent%20unit%20and%20graph%20convolutional%20neural%20network%20for%20non-stationary%20data%20patterns-2024-01-18.pdf.txt https://repositorio.cuc.edu.co/bitstream/11323/10681/4/Advanced%20series%20decomposition%20with%20a%20gated%20recurrent%20unit%20and%20graph%20convolutional%20neural%20network%20for%20non-stationary%20data%20patterns-2024-01-18.pdf.jpg |
| bitstream.checksum.fl_str_mv |
6cb45a61bea2bfa52e3836df8a6f275e 2f9959eaf5b71fae44bbf9ec84150c7a 798cceb65b14e24135f1ba318cacb66a d65ea54f8014b270fb4bfca526a3148e |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Universidad de La Costa |
| repository.mail.fl_str_mv |
bdigital@metabiblioteca.com |
| _version_ |
1808400169177186304 |
| spelling |
Atribución 4.0 Internacional (CC BY 4.0)The Author(s) 2023. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.https://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Han, Huiminfa377cb54087c7e87387c1f211977d1eNeira Molin, Harold5576754ed978a97316d99f233b3799f0Khan, Asad8015423c5ea1ff6d7589751359fd154bFang, Meiec8ce71fbb1b9ec30e7318a79a9ebd205Mahmoud, Haitham A.6de8ea2a01b233da90b23009cd9062acMahrous Awwad, Emad380f927820b77b78cbd23edcfb5b3bafAhmed, Bilalacb17d758d5489d1af676a1e402e75b9Yasin Ghadi, Yazeede48554ca836fc513a2f0e6d05ffaa94c2024-01-31T21:46:46Z2024-01-31T21:46:46Z2024-01-18Han, H., Neira-Molin, H., Khan, A. et al. Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns. J Cloud Comp 13, 20 (2024). https://doi.org/10.1186/s13677-023-00560-1https://hdl.handle.net/11323/1068110.1186/s13677-023-00560-12192-113XCorporación Universidad de la CostaREDICUC - Repositorio CUChttps://repositorio.cuc.edu.coIn this study, we present the EEG-GCN, a novel hybrid model for the prediction of time series data, adept at address ing the inherent challenges posed by the data’s complex, non-linear, and periodic nature, as well as the noise that fre quently accompanies it. This model synergizes signal decomposition techniques with a graph convolutional neural network (GCN) for enhanced analytical precision. The EEG-GCN approaches time series data as a one-dimensional temporal signal, applying a dual-layered signal decomposition using both Ensemble Empirical Mode Decomposi tion (EEMD) and GRU. This two-pronged decomposition process efectively eliminates noise interference and distills the complex signal into more tractable sub-signals. These sub-signals facilitate a more straightforward feature analysis and learning process. To capitalize on the decomposed data, a graph convolutional neural network (GCN) is employed to discern the intricate feature interplay within the sub-signals and to map the interdependencies among the data points. The predictive model then synthesizes the weighted outputs of the GCN to yield the fnal forecast. A key component of our approach is the integration of a Gated Recurrent Unit (GRU) with EEMD within the GCN framework, referred to as EEMD-GRU-GCN. This combination leverages the strengths of GRU in capturing temporal dependencies and the EEMD’s capability in handling non-stationary data, thereby enriching the feature set available for the GCN and enhancing the overall predictive accuracy and stability of the model. Empirical evaluations demonstrate that the EEG-GCN model achieves superior performance metrics. Compared to the baseline GCN model, EEG-GCN shows an average R2 improvement of 60% to 90%, outperforming the other methods. These results substantiate the advanced predictive capability of our proposed model, underscoring its potential for robust and accurate time series forecasting.19 páginasapplication/pdfengSpringer Science + Business MediaUnited Stateshttps://journalofcloudcomputing.springeropen.com/articles/10.1186/s13677-023-00560-1Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patternsArtículo de revistahttp://purl.org/coar/resource_type/c_6501http://purl.org/coar/resource_type/c_2df8fbb1Textinfo:eu-repo/semantics/articlehttp://purl.org/redcol/resource_type/ARTinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/version/c_970fb48d4fbd8a85Journal of Cloud Computing1. Salles R, Pacitti E, Bezerra E, Porto F, Ogasawara E (2022) T S Pred: a framework for nonstationary time series prediction. Neurocomputing 467:197–2022. Goudarzi G, Birgani YT, Assarehzadegan MA, Neisi A, Dastoorpoor M, Sorooshian A, Yazdani M (2022) Prediction of airborne pollen concentra tions by artifcial neural network and their relationship with meteorologi cal parameters and air pollutants. J Environ Health Sci Eng 20(1):251–2643. Méndez M, Merayo MG, Núñez M (2023) Long-term trafc fow forecast ing using a hybrid CNN-BiLSTM model. Eng Appl Artif Intell 121:1060414. Bhatti U, Masud M, Bazai S, Tang H (2023). Editorial: Investigating AI-based smart precision agriculture techniques. Front Plant Sci 14 https://doi.org/ 10.3389/fpls.2023.1237783.5. Fischer E, Barreca G, Greco A et al (2023) Seismic risk assessment of a large metropolitan area by means of simulated earthquakes. Nat Hazards 118:117–1536. Mahmoud A, Mohammed A (2021) A survey on deep learning for timeseries forecasting. In: Hassanien AE, Darwish A. (eds) Machine learning and big data analytics paradigms: analysis, applications and challenges. Studies in Big Data. vol 77. Springer, Cham.7. Guo K, Yu X, Liu G, Tang S (2023) A Long-Term Trafc Flow Prediction Model Based on Variational Mode Decomposition and Auto-Correlation Mechanism. Appl Sci 13:71398. Hahn Y, Langer T, Meyes R, Meisen T (2023) Time Series Dataset Survey for Forecasting with Deep Learning. Forecasting 5:315–3359. Ning Y, Kazemi H, Tahmasebi P (2022) A comparative machine learning study for time series oil production forecasting: ARIMA, LSTM, and Prophet. Comput Geosci 164:10512610. Dong S, Xiao J, Xiaolin Hu, Fang N, Liu L, Yao J (2023) Deep transfer learn ing based on Bi-LSTM and attention for remaining useful life prediction of rolling bearing. Reliab Eng Syst Saf 230:10891411. He R, Zhang C, Xiao Y, Lu X, Zhang S, Yanbing Liu Y (2024) Deep spatiotemporal 3D dilated dense neural network for trafc fow prediction. Expert Syst Appl 237(Part A):121394.12. Yuan Y, Shao C, Cao Z, Chen W, Yin A, Yue H, Xie B (2019) Urban rail transit passenger fow forecasting method based on the coupling of artifcial fsh swarm and improved particle swarm optimization algorithms. Sus tainability 11:723013. Zheng H, Chen J, Huang Z, Yang K, Zhu J (2022) Short-Term Online Fore casting for Passenger Origin-Destination (OD) Flows of urban rail transit: a graph-temporal fused deep learning method. Mathematics 10:366414. Banerjee N, Morton A, Akartunal K (2020) Passenger demand forecasting in scheduled transportation. Eur J Oper Res 286(3):797–81015. Li W, Sui L, Zhou M et al (2021) Short-term passenger fow forecast for urban rail transit based on multi-source data. J Wireless Com Network 2021:916. Toan TD, Truong V-H (2021) Support vector machine for short-term trafc fow prediction and improvement of its model training using nearest neighbor approach. Transp Res Rec 2675(4):362–37317. Liu Y, Rasouli S, Wong M, Feng T, Huang T (2024) RT-GCN: Gaussian-based spatiotemporal graph convolutional network for robust trafc prediction. Inform Fusion 102:10207818. Luo X, Li D, Zhang S (2019) Trafc Flow Prediction during the Holidays Based on DFT and SVR. Journal of Sensors 2019:1–10. https://doi.org/10. 1155/2019/646145019. Ma C, Zhao Y, Dai G, Xu X, Wong SC (2022). A novel STFSA-CNN-GRU Hybrid model for short-term trafc speed prediction. IEEE Transact Intell Transport Systems. PP. 1–10. https://doi.org/10.1109/TITS.2021.3117835.20. Wang S, Shao C, Zhang J, Zheng Y, Meng M (2022) Trafc fow prediction using bi-directional gated recurrent unit method. Urban Inform 1(1):1621. Zafar N, Haq IU, Chughtai JU, Shafq O (2022) Applying Hybrid Lstm-Gru Model Based on Heterogeneous Data Sources for Trafc Speed Prediction in Urban Areas. Sensors (Basel)22(9):3348 22. Zhang W, Yao R, Du X, Ye J. (2021). Hybrid deep spatio-temporal models for trafc fow prediction on holidays and under adverse weather. IEEE Access. PP. 1–1. https://doi.org/10.1109/ACCESS.2021.3127584.23. Bhatti UA, Huang M, Neira-Molina H, Marjan S, Baryalai M, Tang H, Wu G, Bazai SU (2023) MFFCG – Multi feature fusion for hyperspectral image classifcation using graph attention network. Expert Syst Appl 229 (Part A):12049624. Fodstad M, del Granado PC, Hellemo L, Knudsen BR, Pisciella P, Silvast A, Bordin C, Schmidt S, Straus J (2022) Next frontiers in energy system modelling: a review on challenges and the state of the art. Renew Sustain Energy Rev 160:112246.25. Joe P, Sun J, Yussouf N, Goodman S, Riemer M, Gouda KC, Golding B, Rogers R, Isaac G, Wilson J, Li PW, Wulfmeyer V, Elmore K, Onvlee J, Chong P and Ladue J (2022) Predicting the weather: a partnership of observa tion scientists and forecasters. In: Golding, B. (eds) Towards the “Perfect” Weather Warning. Springer, Cham.26. Yan J, Möhrlen C, Göçmen T, Kelly M, Wessel A, Giebel G (2022) Uncover ing wind power forecasting uncertainty sources and their propaga tion through the whole modelling chain. Renew Sustain Energy Rev 165:11251927. Wang H (2023) Extreme learning Kalman flter for short-term wind speed prediction. Front Energy Res 10:1047381. https://doi.org/10.3389/fenrg. 2022.104738128. Fattah J, Ezzine L, Aman Z, El Moussami H, Lachhab A 2018 Forecasting of demand using ARIMA model. Int J Eng Bus Manag 10.29. Hanif S, Lotfan S, Zare-Behtash H, Cammarano A (2022) Ofshore wind power forecasting—A new hyperparameter optimisation algorithm for deep learning models. Energies 15:691930. Ospina R, Gondim JAM, Leiva V, Castro C (2023) An overview of forecast analysis with ARIMA Models during the COVID-19 Pandemic: methodol ogy and case study in Brazil. Mathematics 11:306931. Wang S, Wang J, Haiyan Lu, Zhao W (2021) A novel combined model for wind speed prediction – Combination of linear model, shallow neural networks, and deep learning approaches. Energy 234:12127532. Nair KR, Vanitha V and Jisma M (2017) Forecasting of wind speed using ANN, ARIMA and Hybrid models, 2017 International Conference on Intel ligent Computing, Instrumentation and Control Technologies (ICICICT), Kerala, India, 2017, pp. 170–175,33. Liu H, Tian H-q, Li Y-F (2012) Comparison of two new ARIMA-ANN and ARIMA-Kalman hybrid methods for wind speed prediction. Appl Energy 98:415–42434. Aasim SN, Singh AM (2019) Repeated wavelet transform based ARIMA model for very short-term wind speed forecasting. Renew Energy 136:758–768.35. Bhatti UA, Hashmi MZ, Sun Y, Masud M, Nizamani MM (2023) Editorial: Artifcial intelligence applications in reduction of carbon emissions: Step towards sustainable environment. Front Environ Sci 11:118362036. Zhang X, Wu X, Zhu G, Lu X, Wang K (2022) A seasonal ARIMA model based on the gravitational search algorithm (GSA) for runof prediction. Water Supply 22(8): 6959–6977.37. Wang H, Yan S, Ju D, Ma N, Fang J, Wang S, Li H, Zhang T, Xie Y, Wang J (2023) Short-term photovoltaic power forecasting based on a feature rise-dimensional two-layer ensemble learning model. Sustainability 15:1559438. Shuai Hu, Xiang Y, Zhang H, Xie S, Li J, Chenghong Gu, Sun W, Liu J (2021) Hybrid forecasting method for wind power integrating spatial correlation and corrected numerical weather prediction. Appl Energy 293:11695139. Nawab F, Abd Hamid AS, Ibrahim A, Sopian K, Fazlizan A, Fauzan MF (2023) Solar irradiation prediction using empirical and artifcial intel ligence methods: a comparative review. Heliyon 9(6)40. Deng Y, Zhou X, Shen J, Xiao G, Hong H, Lin H, Wu F, Liao BQ (2021) New methods based on back propagation (BP) and radial basis function (RBF) artifcial neural networks (ANNs) for predicting the occurrence of halok etones in tap water. Sci Total Environ 10(772):14553441. Ellahi M, Usman MR, Arif W, Usman HF, Khan WA, Satrya GB, Daniel K, Shabbir N (2022) Forecasting of wind speed and power through FFNN and CFNN using HPSOBA and MHPSO-BAACs techniques. Electronics 11:419342. Chen N, Xiong C, Du W, Wang C, Lin X, Chen Z (2019) An Improved Genetic Algorithm Coupling a Back-Propagation Neural Network model (IGA-BPNN) for water-level predictions. Water 11:179543. Bhatti UA, Tang H, Wu G, Marjan S, Hussain A (2023) Deep learning with graph convolutional networks: an overview and latest applications in computational intelligence. Int J Intell Syst 2023:1–2844. Al-Majidi SD, Abbod MF, Al-Raweshidy HS (2020) A particle swarm optimi sation-trained feedforward neural network for predicting the maximum power point of a photovoltaic array. Eng Appl Artif Intell 92:10368845. Husein M, Chung IY. Day-ahead solar irradiance forecasting for microgrids using a long short-term memory recurrent neural network: A deep learn ing approach. Energies. 2019;12(10):1856.46. Uncuoglu E, Citakoglu H, Latifoglu L, Bayram S, Laman M, Mucella Ilkentapar, Alper Oner AA (2022) Comparison of neural network, Gaussian regression, support vector machine, long short-term memory, multigene genetic programming, and M5 Trees methods for solving civil engineering problems. Appl Soft Comput 129:10962347. Zhang C, Zhang M (2022) Wavelet-based neural network with genetic algorithm optimization for generation prediction of PV plants. Energy Rep 8:10976–1099048. Park R-J, Song K-B, Kwon B-S (2020) Short-term load forecasting algorithm using a similar day selection method based on reinforcement learning. Energies 13:264049. Bhatti U, Bazai S, Hussain S, Fakhar S, Ku C, Marjan S, Por Y, Jing L (2023). Deep learning-based trees disease recognition and classifcation using hyperspectral data. Compu Mat Continua 77:681–697. https://doi.org/10. 32604/cmc.2023.037958.50. Gagnon P, Cole W (2022) Planning for the evolution of the electric grid with a long-run marginal emission rate. iScience 25(3):103915.51. Almani AA, Han X (2023) Real-time pricing-enabled demand response using long short-time memory deep learning. Energies 16:241052. Barton M, Lennox B (2022) Model stacking to improve prediction and variable importance robustness for soft sensor development. Digital Chem Eng 353. Zheng H, Yuan J, Chen L (2017) Short-term load forecasting using emdlstm neural networks with a Xgboost algorithm for feature importance evaluation. Energies 10:116854. Vanting NB, Ma Z, Jørgensen BN (2021) A scoping review of deep neural networks for electric load forecasting. Energy Inform 4(Suppl 2):4955. Xu Y, Liu X, Cao X, Huang C, Liu E, Qian S, Liu X, Yanjun Wu, Dong F, Qiu C-W, Qiu J, Hua K, Wentao Su, Jian Wu, Huiyu Xu, Han Y, Chenguang Fu, Yin Z, Liu M, Roepman R, Dietmann S, Virta M, Kengara F, Zhang Ze, Zhang L, Zhao T, Dai Ji, Yang J, Lan L, Luo M, Liu Z, An T, Zhang B, He X, Cong S, Liu X, Zhang W, Lewis JP, Tiedje JM, Wang Qi, An Z, Wang F, Zhang L, Huang T, Chuan Lu, Cai Z, Wang F, Zhang J (2021) Artifcial intelligence: a powerful paradigm for scientifc research. Innovation 2(4):10017956. Ullah I, Muhammad Hasanat S, Aurangzeb K, Alhussein M, Rizwan M, Anwar MS (2023) Multi-horizon short-term load forecasting using hybrid of LSTM and modifed split convolution. PeerJ Comput Sci 15(9):e148757. Muhammad Ahsan Zamee, Dongjun Han, Heejune Cha, Dongjun Won (2023) Self-supervised online learning algorithm for electric vehicle charging station demand and event prediction. J Energy Storage 71:108189.58. Zheng J, Zhu J, Xi H (2023) Short-term energy consumption prediction of electric vehicle charging station using attentional feature engineering and multi-sequence stacked Gated Recurrent Unit. Comput Electr Eng 108:10869459. He W, Li Z, Liu T, Liu Z, Guo X, Jinguang Du, Li X, Sun P, Ming W (2023) Research progress and application of deep learning in remaining useful life, state of health and battery thermal management of lithium batteries. J Energy Storage 70:10786860. Bhatia K, Mittal R, Varanasi J, Tripathi MM (2021) An ensemble approach for electricity price forecasting in markets with renewable energy resources. Utilities Policy 70:101185.61. Xinxin W, Xiaopan S, Xueyi A, Shijia L (2023) Short-term wind speed fore casting based on a hybrid model of ICEEMDAN, MFE, LSTM and informer. PLoS One 18(9):e028916162. Zhao L, Li Z, Zhang J, Teng B (2023) An integrated complete ensemble empirical mode decomposition with adaptive noise to optimize LSTM for signifcant wave height forecasting. J Mar Sci Eng 11:43563. Liu H, Xiong X, Yang B, Cheng Z, Shao K, Tolba A (2023) A power load fore casting method based on intelligent data analysis. Electronics 12:344164. Nepal B, Yamaha M, Yokoe A, Yamaji T (2020) Electricity load forecasting using clustering and ARIMA model for energy management in buildings. Jpn Archit Rev 3:62–7665. Saglam M, Spataru C, Karaman OA (2023) Forecasting electricity demand in Turkey using optimization and machine learning algorithms. Energies 16:449966. Henrique BM, Sobreiro VA, Kimura H (2018) Stock price prediction using support vector regression on daily and up to the minute prices. J Finance Data Sci 4(3):183–201.67. Gupta D, Pratama M, Ma Z, Li J, Prasad M (2019) Financial time series forecasting using twin support vector regression. PLoS One 14(3)68. Ashfaq T and Javaid N (2019) "Short-term electricity load and price fore casting using enhanced KNN," 2019 International Conference on Frontiers of Information Technology (FIT), Islamabad, Pakistan, pp. 266–2665.69. Maleki H, Sorooshian A, Goudarzi G, Baboli Z, Birgani YT, Rahmati M (2019) Air pollution prediction by using an artifcial neural network model. Clean Technol Environ Policy 21(6):1341–135270. Sarker IH (2021) Deep Learning: a comprehensive overview on tech niques, taxonomy, applications and research directions. Sn Comput Sci 2:42071. Zha W, Liu Y, Wan Y, Luo R, Li D, Yang S, Yanmei Xu (2022) Forecasting monthly gas feld production based on the CNN-LSTM model. Energy 260:12488972. Zhang Q, Jin Q, Chang J, et al (2018) Kernel-weighted graph convolu tional network: a deep learning approach for trafc forecasting[C]//2018 24th International Conference on Pattern Recognition (ICPR). IEEE 1018–1023.73. Yin H, Zuhong Ou, Huang S, Meng A (2019) A cascaded deep learning wind power prediction approach based on a two-layer of mode decom position. Energy 189:11631674. Zhang J, Siya W, Zhongfu T, Anli S (2023) An improved hybrid model for short term power load prediction. Energy 268:12656175. Shu W, Gao Q (2020) Forecasting stock price based on frequency compo nents by EMD and neural networks. Ieee Access 8:206388–20639576. Wu YX, Wu QB, Zhu JQ (2019) Improved EEMD-based crude oil price forecasting using LSTM networks. Physica A 516:114–12477. Yin C, Wang G, Liao J (2023) Application of VMD–SSA–BiLSTM algorithm to smart grid fnancial market time series forecasting and sustainable innovation management. Front Energy Res 11:12395421201319Time series forecastingEEMDCEEMDANGCNORIGINALAdvanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns-2024-01-18.pdfAdvanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns-2024-01-18.pdfArtículoapplication/pdf2561331https://repositorio.cuc.edu.co/bitstream/11323/10681/1/Advanced%20series%20decomposition%20with%20a%20gated%20recurrent%20unit%20and%20graph%20convolutional%20neural%20network%20for%20non-stationary%20data%20patterns-2024-01-18.pdf6cb45a61bea2bfa52e3836df8a6f275eMD51open accessLICENSElicense.txtlicense.txttext/plain; charset=utf-814828https://repositorio.cuc.edu.co/bitstream/11323/10681/2/license.txt2f9959eaf5b71fae44bbf9ec84150c7aMD52open accessTEXTAdvanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns-2024-01-18.pdf.txtAdvanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns-2024-01-18.pdf.txtExtracted texttext/plain76748https://repositorio.cuc.edu.co/bitstream/11323/10681/3/Advanced%20series%20decomposition%20with%20a%20gated%20recurrent%20unit%20and%20graph%20convolutional%20neural%20network%20for%20non-stationary%20data%20patterns-2024-01-18.pdf.txt798cceb65b14e24135f1ba318cacb66aMD53open accessTHUMBNAILAdvanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns-2024-01-18.pdf.jpgAdvanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns-2024-01-18.pdf.jpgGenerated Thumbnailimage/jpeg12700https://repositorio.cuc.edu.co/bitstream/11323/10681/4/Advanced%20series%20decomposition%20with%20a%20gated%20recurrent%20unit%20and%20graph%20convolutional%20neural%20network%20for%20non-stationary%20data%20patterns-2024-01-18.pdf.jpgd65ea54f8014b270fb4bfca526a3148eMD54open access11323/10681oai:repositorio.cuc.edu.co:11323/106812024-02-01 03:03:09.903An error occurred on the license name.|||https://creativecommons.org/licenses/by/4.0/open accessRepositorio Universidad de La Costabdigital@metabiblioteca.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 |