FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386187721> ?p ?o ?g. }

• W4386187721 endingPage "121202" @default.
• W4386187721 startingPage "121202" @default.
• W4386187721 abstract "Long short-term memory faces challenges in information mining and parameter selection due to inherent uncertainty and randomness. In this study, we propose a novel hybrid model called ‘STL-ALN_BSA-LSTM’ that aims to tackle this issue. In the proposed model, data is first prepossessed using seasonal-trend decomposition to extract informative features. Next, we propose an adaptive learning and niching-based backtracking search algorithm to enhance the robustness and learning ability of the original backtracking search algorithm, which affords a balance between exploration and exploitation. Subsequently, the weights and thresholds within each LSTM are optimized by our optimization algorithm automatically, leading to improved interpretability and accuracy of the model. Finally, the proposed optimization algorithm was evaluated using five benchmark functions, and the hybrid model was compared with sixteen baselines on two real-world datasets. For rainfall forecasting, the hybrid model achieved the root mean square error of 7.3772, mean absolute error of 2.6187, and R2 of 0.8388. For power generation forecasting, our model outperformed the second-best model by 29.6%, 34.4%, and 16 ‰, respectively, as in the above metrics. These results demonstrate that the proposed hybrid model can attain higher accuracy in real-life applications than previous models, which contributes in-depth insights into parameter optimization for time series forecasting, and provides valuable suggestions in resource planning, risk reduction, and decision-making. The core code of this work can be found from https://github.com/zjuml/STL-ALNBSA-LSTM." @default.
• W4386187721 created "2023-08-27" @default.
• W4386187721 creator A5010446083 @default.
• W4386187721 creator A5039902709 @default.
• W4386187721 creator A5048149397 @default.
• W4386187721 creator A5048635843 @default.
• W4386187721 creator A5050960677 @default.
• W4386187721 creator A5052354240 @default.
• W4386187721 creator A5087765996 @default.
• W4386187721 date "2024-02-01" @default.
• W4386187721 modified "2023-09-29" @default.
• W4386187721 title "Effective LSTMs with seasonal-trend decomposition and adaptive learning and niching-based backtracking search algorithm for time series forecasting" @default.
• W4386187721 cites W1546359014 @default.
• W4386187721 cites W1968075052 @default.
• W4386187721 cites W1987092188 @default.
• W4386187721 cites W1999284878 @default.
• W4386187721 cites W2064675550 @default.
• W4386187721 cites W2093275097 @default.
• W4386187721 cites W2284304237 @default.
• W4386187721 cites W2319697090 @default.
• W4386187721 cites W2529154472 @default.
• W4386187721 cites W2588846930 @default.
• W4386187721 cites W2606283685 @default.
• W4386187721 cites W2621177957 @default.
• W4386187721 cites W2766596991 @default.
• W4386187721 cites W2802586787 @default.
• W4386187721 cites W2919115771 @default.
• W4386187721 cites W2920714358 @default.
• W4386187721 cites W2938111495 @default.
• W4386187721 cites W2947242643 @default.
• W4386187721 cites W2947350869 @default.
• W4386187721 cites W2958456210 @default.
• W4386187721 cites W2964758013 @default.
• W4386187721 cites W2968462207 @default.
• W4386187721 cites W2983352457 @default.
• W4386187721 cites W2983873244 @default.
• W4386187721 cites W2989662765 @default.
• W4386187721 cites W3017786565 @default.
• W4386187721 cites W3025296742 @default.
• W4386187721 cites W3027972301 @default.
• W4386187721 cites W3035376600 @default.
• W4386187721 cites W3036643472 @default.
• W4386187721 cites W3043561841 @default.
• W4386187721 cites W3080157892 @default.
• W4386187721 cites W3089152325 @default.
• W4386187721 cites W3093332445 @default.
• W4386187721 cites W3109365969 @default.
• W4386187721 cites W3111334809 @default.
• W4386187721 cites W3118551694 @default.
• W4386187721 cites W3121052081 @default.
• W4386187721 cites W3137429615 @default.
• W4386187721 cites W3138340468 @default.
• W4386187721 cites W3157032429 @default.
• W4386187721 cites W3159573745 @default.
• W4386187721 cites W3170702380 @default.
• W4386187721 cites W3174537966 @default.
• W4386187721 cites W3182635198 @default.
• W4386187721 cites W3192682950 @default.
• W4386187721 cites W3194817114 @default.
• W4386187721 cites W3197065975 @default.
• W4386187721 cites W3203014857 @default.
• W4386187721 cites W3206980818 @default.
• W4386187721 cites W4213021104 @default.
• W4386187721 cites W4221048209 @default.
• W4386187721 cites W4224220755 @default.
• W4386187721 cites W4224986685 @default.
• W4386187721 cites W4225243270 @default.
• W4386187721 cites W4253953323 @default.
• W4386187721 cites W4281673375 @default.
• W4386187721 cites W4281700753 @default.
• W4386187721 cites W4281871161 @default.
• W4386187721 cites W4283734450 @default.
• W4386187721 cites W4285191770 @default.
• W4386187721 cites W4285507321 @default.
• W4386187721 cites W4285793941 @default.
• W4386187721 cites W4288050066 @default.
• W4386187721 cites W4293059482 @default.
• W4386187721 cites W4309120572 @default.
• W4386187721 cites W4313570468 @default.
• W4386187721 cites W4313594206 @default.
• W4386187721 cites W4315928998 @default.
• W4386187721 cites W4316136053 @default.
• W4386187721 cites W4317629012 @default.
• W4386187721 cites W4318185035 @default.
• W4386187721 cites W4321496350 @default.
• W4386187721 cites W4353072294 @default.
• W4386187721 cites W4367304450 @default.
• W4386187721 cites W4375947639 @default.
• W4386187721 cites W4376114895 @default.
• W4386187721 cites W4382203079 @default.
• W4386187721 cites W4382247920 @default.
• W4386187721 cites W4384283279 @default.
• W4386187721 doi "https://doi.org/10.1016/j.eswa.2023.121202" @default.
• W4386187721 hasPublicationYear "2024" @default.
• W4386187721 type Work @default.
• W4386187721 citedByCount "0" @default.
• W4386187721 crossrefType "journal-article" @default.
• W4386187721 hasAuthorship W4386187721A5010446083 @default.

• next