Hybrid intelligence models for compressive strength prediction of MPC composites and parametric analysis with SHAP algorithm

Materials Today Communications, Год журнала: 2023, Номер 35, С. 105547 - 105547

Опубликована: Фев. 3, 2023

Язык: Английский

---

Recurrent Neural Networks: A Comprehensive Review of Architectures, Variants, and Applications

Information, Год журнала: 2024, Номер 15(9), С. 517 - 517

Опубликована: Авг. 25, 2024

Recurrent neural networks (RNNs) have significantly advanced the field of machine learning (ML) by enabling effective processing sequential data. This paper provides a comprehensive review RNNs and their applications, highlighting advancements in architectures, such as long short-term memory (LSTM) networks, gated recurrent units (GRUs), bidirectional LSTM (BiLSTM), echo state (ESNs), peephole LSTM, stacked LSTM. The study examines application to different domains, including natural language (NLP), speech recognition, time series forecasting, autonomous vehicles, anomaly detection. Additionally, discusses recent innovations, integration attention mechanisms development hybrid models that combine with convolutional (CNNs) transformer architectures. aims provide ML researchers practitioners overview current future directions RNN research.

Язык: Английский

---

A Critical Review of RNN and LSTM Variants in Hydrological Time Series Predictions

MethodsX, Год журнала: 2024, Номер 13, С. 102946 - 102946

Опубликована: Сен. 12, 2024

Язык: Английский

---

Recurrent Neural Networks: A Comprehensive Review of Architectures, Variants, and Applications

Опубликована: Авг. 12, 2024

Recurrent Neural Networks (RNNs) have significantly advanced the field of machine learning by enabling effective processing sequential data. This paper provides a comprehensive review RNNs and their applications, highlighting advancements in architectures such as Long Short-Term Memory (LSTM) networks, Gated Units (GRUs), Bidirectional LSTM (BiLSTM), stacked LSTM. The study examines application different domains, including natural language (NLP), speech recognition, financial time series forecasting, bioinformatics, autonomous vehicles, anomaly detection. Additionally, discusses recent innovations, integration attention mechanisms development hybrid models that combine with convolutional neural networks (CNNs) transformer architectures. aims to provide researchers practitioners overview current state future directions RNN research.

Язык: Английский

---

Implementing a novel deep learning technique for rainfall forecasting via climatic variables: An approach via hierarchical clustering analysis

The Science of The Total Environment, Год журнала: 2022, Номер 854, С. 158760 - 158760

Опубликована: Сен. 13, 2022

Язык: Английский

---

Application of Artificial Intelligence for EV Charging and Discharging Scheduling and Dynamic Pricing: A Review

Energies, Год журнала: 2022, Номер 16(1), С. 146 - 146

Опубликована: Дек. 23, 2022

The high penetration of electric vehicles (EVs) will burden the existing power delivery infrastructure if their charging and discharging are not adequately coordinated. Dynamic pricing is a special form demand response that can encourage EV owners to participate in scheduling programs. Therefore, its dynamic model important fields study. Many researchers have focused on artificial intelligence-based forecasting models suggested intelligence techniques perform better than conventional optimization methods such as linear, exponential, multinomial logit models. However, only few research studies (i.e., vehicle-to-grid, V2G) because concept electricity back grid relatively new evolving. review discharging-related needed understand gaps make some improvements future studies. This paper reviews classifies them into forecasting, scheduling, mechanisms. determines linkage between mechanism identifies

Язык: Английский

---

Lithium-ion battery state of health estimation using a hybrid model based on a convolutional neural network and bidirectional gated recurrent unit

Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 127, С. 107199 - 107199

Опубликована: Окт. 9, 2023

Язык: Английский

---

A Novel Approach for Short-Term Energy Forecasting in Smart Buildings

IEEE Sensors Journal, Год журнала: 2023, Номер 23(5), С. 5307 - 5314

Опубликована: Янв. 26, 2023

Efficient energy management is required for optimal consumption. The building sector consumes 40% of the total global production and expected to reach 50% by 2050. With soaring price electricity, buildings need economical efficient management. Recent advances in artificial intelligence Internet Things (IoT) have inspired researchers working smart harness potential these technologies forecasting consumption buildings. This article proposes a novel hybrid deep learning model consisting convolutional neural network (CNN) recurrent (RNN) predict hourly Experimental results demonstrate that CNN-gated unit (GRU) model, with an accuracy 97%, outperforms state-of-the-art techniques.

Язык: Английский

---

Time series forecasting of oil production in Enhanced Oil Recovery system based on a novel CNN-GRU neural network

Geoenergy Science and Engineering, Год журнала: 2023, Номер 233, С. 212528 - 212528

Опубликована: Ноя. 28, 2023

Язык: Английский

---

A Diffusion–Attention-Enhanced Temporal (DATE-TM) Model: A Multi-Feature-Driven Model for Very-Short-Term Household Load Forecasting

Energies, Год журнала: 2025, Номер 18(3), С. 486 - 486

Опубликована: Янв. 22, 2025

With the proliferation of smart home devices and ever-increasing demand for household energy management, very-short-term load forecasting (VSTLF) has become imperative usage optimization, cost saving sustaining grid stability. Despite recent advancements, VSTLF in scenario still poses challenges. For instance, some characteristics (e.g., high-frequency, noisy non-stationary) exacerbate data processing model training procedures, heterogeneity consumption patterns causes difficulties models with generalization capability. Further, real-time requirement calls both high accuracy improved computational efficiency. Thus, we propose a diffusion–attention-enhanced temporal (DATE-TM) multi-feature fusion to address above issues. First, DATE-TM could integrate residents’ electricity climatic factors. Then, it extracts feature using an encoder meanwhile uncertainty through diffusion model. Finally, decoder, enhanced attention mechanism, creates precise prediction forecasting. Experimental results reveal that significantly surpasses classical neural networks such as BiLSTM DeepAR, especially handling long-term dependency.

Язык: Английский

---