FD-LSTM: A Fuzzy LSTM Model for Chaotic Time-Series Prediction

被引：7

作者：

Langeroudi, Milad Keshtkar ^{[1
]}

Yamaghani, Mohammad Reza ^{[1
]}

Khodaparast, Siavash ^{[2
]}

机构：

[1] Islamic Azad Univ, Dept Comp Engn, Lahijan Branch, Lahijan 4416939515, Iran

[2] Islamic Azad Univ, Dept Phys & Sport Sci, Lahijan Branch, Lahijan 4416939515, Iran

来源：

IEEE INTELLIGENT SYSTEMS | 2022年 / 37卷 / 04期

关键词：

Deep Learning; LSTM; Time-Series Prediction; Type-2 fuzzy system;

D O I：

10.1109/MIS.2022.3179843

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The main issue of time-series prediction is to determine the grade of uncertainty in knowledge, with its essential vagueness and haziness in complex problems. In this study, a deep fuzzy long short-term memory (LSTM) architecture has been proposed to handle the high-order uncertainty associated with time-series applications. The LSTM and type-2 fuzzy logic combination aim to make a more transparent, interpretable, and accurate predictive system. The experiments of this study with real data contain global standard and real-valued benchmarks, including MackeyGlass (MG), sunspot, and English Premier League seasonal datasets. The obtained performance shows the superiority of the proposed fuzzy-deep model in predicting time series with an average AUC = 0.96 in sunspot, 0.93 for football match time series, and 0.95 on a chaotic equation of MG.

引用

页码：70 / 78

页数：9

共 50 条

[1] Time Series Prediction Based on LSTM-Attention-LSTM Model
Wen, Xianyun
Li, Weibang
[J]. IEEE ACCESS, 2023, 11 : 48322 - 48331
[2] Multivariate Time-Series Prediction Using LSTM Neural Networks
Ghanbari, Reza
Borna, Keivan
[J]. 2021 26TH INTERNATIONAL COMPUTER CONFERENCE, COMPUTER SOCIETY OF IRAN (CSICC), 2021,
[3] Transductive LSTM for time-series prediction: An application to weather forecasting
Karevan, Zahra
Suykens, Johan A. K.
[J]. NEURAL NETWORKS, 2020, 125 : 1 - 9
[4] Medical Time-series Prediction With LSTM-MDN-ATTN
Park, Hwin Dol
Han, Youngwoong
Choi, Jae Hun
[J]. 2019 10TH INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGY CONVERGENCE (ICTC): ICT CONVERGENCE LEADING THE AUTONOMOUS FUTURE, 2019, : 1359 - 1361
[5] Based on the Improved PSO-TPA-LSTM Model Chaotic Time Series Prediction
Cai, Zijian
Feng, Guolin
Wang, Qiguang
[J]. ATMOSPHERE, 2023, 14 (11)
[6] Multivariate CNN-LSTM Model for Multiple Parallel Financial Time-Series Prediction
Widiputra, Harya
Mailangkay, Adele
Gautama, Elliana
[J]. COMPLEXITY, 2021, 2021
[7] A Sensitive LSTM Model for High Accuracy Zero-Inflated Time-Series Prediction
Huang, Zhixin
Lin, Jiaxiang
Lin, Lizheng
Chen, Jianyun
Zheng, Liankai
Zhang, Keju
[J]. IEEE Access, 2024, 12 : 171527 - 171539
[8] SCE-LSTM: Sparse Critical Event-Driven LSTM Model with Selective Memorization for Agricultural Time-Series Prediction
Ryu, Ga-Ae
Chuluunsaikhan, Tserenpurev
Nasridinov, Aziz
Rah, Hyungchul
Yoo, Kwan-Hee
Pantazi, Xanthoula Eirini
[J]. AGRICULTURE-BASEL, 2023, 13 (11):
[9] A CNN–LSTM model for gold price time-series forecasting
Ioannis E. Livieris
Emmanuel Pintelas
Panagiotis Pintelas
[J]. Neural Computing and Applications, 2020, 32 : 17351 - 17360
[10] LSTM based Time-series Prediction for Optimal Scheduling in the Foundry Industry
Rose, Alexander
Grotjahn, Martin
[J]. 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,

← 1 2 3 4 5 →