Related references
Note: Only part of the references are listed.
Article
Meteorology & Atmospheric Sciences
Wei Wang et al.
Summary: In this study, two deep learning models, DeepPM and APTR, were constructed and trained to improve the forecasting effectiveness of numerical air quality models. The results showed that these models significantly outperformed the WRF-Chem numerical model in both short-term and medium-term forecasts.
ATMOSPHERIC RESEARCH
(2022)
Review
Computer Science, Artificial Intelligence
Mahinda Mailagaha Kumbure et al.
Summary: This literature review explores the application of machine learning techniques in stock market prediction. It focuses on the stock markets investigated in the literature and the types of variables used as input in machine learning techniques for predicting these markets. The review includes an examination of 138 journal articles published between 2000 and 2019 and provides extensive insights into the data and machine learning techniques used for stock market prediction.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Jun Yu et al.
Summary: This paper proposes a method to predict the click feature of an image from visual features by integrating sparse constraints and an improved RELU operator. The method learns from an auxiliary image dataset containing click information to discover the hierarchy of word semantics. Experimental results show that the method achieves higher recognition accuracy, larger compression ratio, and good one-shot learning ability and scalability to unseen categories.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Engineering, Civil
Kyeungwoo Cho et al.
Summary: Researchers propose a method combining WRF-Hydro and LSTM network, called WRF-Hydro-LSTM, to improve streamflow simulations. Experimental results show that WRF-Hydro-LSTM outperforms both traditional methods and using LSTM alone in streamflow prediction.
JOURNAL OF HYDROLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Madini O. Alassafi et al.
Summary: The study developed a prediction model for the spread of COVID-19 in Malaysia, Morocco, and Saudi Arabia using public datasets from the European Centre for Disease Prevention and Control. Deep learning models were utilized with a focus on LSTM networks. The study also compared the number of cases and deaths in the three countries.
Article
Computer Science, Artificial Intelligence
Dianxi Shi et al.
Summary: Deep reinforcement learning has shown remarkable progress in multi-agent tasks, but most studies have focused on fully cooperative tasks rather than mixed tasks. To address the challenges of mixed tasks, a new approach using attention mechanism for information representation is proposed, which achieves efficiency through a framework of centralized training and decentralized execution.
Article
Environmental Sciences
Jiawei Tian et al.
Summary: Smog pollution is a significant global problem requiring further research and prediction. This paper proposes a deep learning technology based on a Deep Belief-Back Propagation neural network to predict and prevent smog pollution using air pollution data in Sichuan. The results show that the prediction accuracy is higher with more hidden layers, and PM2.5 can be predicted more accurately than PM10 using this network.
Article
Computer Science, Interdisciplinary Applications
Sebastiano Marasco et al.
Summary: Recent developments in scientific computation and Machine Learning have led to the emergence of algorithms capable of interpreting data and predicting results. This paper introduces a robust Evolutionary Polynomial Bayesian Regression (EPBR) algorithm and applies it to experimental shear strength data of Reinforced Concrete (RC) beams.
ADVANCES IN ENGINEERING SOFTWARE
(2022)
Article
Engineering, Civil
Jerry Jose et al.
Summary: This study aims to develop a scale invariant relationship based on the framework of Universal Multifractals (UM) to calculate the impact of rainfall on particle detachment and soil erosion. Rainfall data was collected using optical disdrometers, and a new power law relation was developed and tested against theoretical assumptions. The equation developed using scale invariant features of UM performs well across scales.
JOURNAL OF HYDROLOGY
(2022)
Article
Energy & Fuels
Xiangling Li et al.
Summary: A deep learning method based on the LSTM neural network model was established to predict well performance considering manual operations, showing better prediction accuracy and relevance of the initial three step inputs for subsequent predictions. The model takes into account manual operations such as opening and closing of wells, changing the size of chokes, and variations in daily production time, providing more reasonable results.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Engineering, Biomedical
Kunye Feng et al.
Summary: This paper proposes an improved bidirectional long short term memory (IB-LSTM) model for intelligence-based classification of atrial fibrillation (AF) signals. With preprocessing steps, the model shows good performance in accuracy and computation cost, and serves as an efficient auxiliary tool for medical diagnosis.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Computer Science, Information Systems
Jiateng Yin et al.
Summary: This study proposes a novel long short-term memory model (LAG-LSTM) with lagged information for the design of automatic train operation and real-time traffic management systems in high-speed railways. By combining the physical-driven HST model and an interpretable deep learning model, our LAG-LSTM accurately predicts the trajectories of HSTs and outperforms other deep learning models in terms of prediction accuracy.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Rui Ye et al.
Summary: This paper introduces a deep learning method for multi-step regional wind speed prediction, aiming to model the spatiotemporal dynamics of wind speed and make predictions across time steps. The proposed method addresses several challenges and achieves promising results in experiments.
INFORMATION SCIENCES
(2022)
Article
Energy & Fuels
Zheng Li et al.
Summary: This research proposes an improved Sparrow Search Algorithm-Least Squares Support Vector Machine (ISSA-LS-SVM) prediction model based on chaotic sequences to enhance the convergence accuracy and reduce the prediction time. Experimental results demonstrate that the proposed model outperforms other existing models and is significant for optimizing power dispatch.
Article
Construction & Building Technology
Han Luo et al.
Summary: The study proposed a framework for predicting construction machine poses based on historical motion data and activity attributes, achieved decent performance in excavator experiments with an average percentage of correct keypoints (PCK) of 90.22%, showing high potential in predicting construction machine poses and improving on-site safety.
AUTOMATION IN CONSTRUCTION
(2021)
Article
Engineering, Biomedical
Aboli N. Londhe et al.
Summary: Researchers are actively investigating methods using advanced machine learning techniques for ECG wave detection, however, current approaches lack generalization, robustness, reliability, and real-time implementation. This study proposes a new approach called semantic segmentation for ECG wave segmentation, utilizing a hybrid channel-mix convolutional and bidirectional LSTM model to extract temporal dependencies in forward and backward timestamps.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Computer Science, Information Systems
Xin Yang et al.
Summary: A novel Wave-LSTM model is introduced for high-precision short-term inbound passenger flow prediction, outperforming existing algorithms in terms of prediction accuracy. Empirical study demonstrates the promising approach of the hybrid model for predicting high-precision short-term inbound passenger flow.
INFORMATION SCIENCES
(2021)
Article
Geology
Seyed Mehran Heidari et al.
Summary: This study aims to detect the distribution of gold and copper mineralization stages in the Gouzal-Bolagh deposit in northwestern Iran using zonality index and S-A multifractal modeling based on geological and surface lithogeochemical data. The results indicate the presence of three mineralization stages (Pre-, main, and post-mineralization) with two sub-stages in the main stage (A: Quartz vein and veinlet sulfidation, B: Quartz sulfide brecciation). The study shows major occurrences of gold and copper mineralization in the sulfidation and brecciation sub-stages.
ORE GEOLOGY REVIEWS
(2021)
Article
Computer Science, Information Systems
Shao-Chun Wen et al.
Summary: The paper introduces a framework for predicting the value of time series for nonlinear systems, including four nonlinear systems and three learning parts. K-means method and MAE are used to evaluate the prediction accuracy.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Interdisciplinary Applications
Jose Mejia et al.
Summary: The study presents an architecture for predicting time series with nonlinear dependencies by combining convolutional and LSTM layers, showing better results compared to other methods in various error measures.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Petronio Candido de Lima e Silva et al.
APPLIED SOFT COMPUTING
(2020)
Article
Nuclear Science & Technology
Bo Wang et al.
ANNALS OF NUCLEAR ENERGY
(2020)
Article
Thermodynamics
Yu Zhang et al.
Proceedings Paper
Automation & Control Systems
Yanrui Li et al.
Article
Telecommunications
Ai Dong et al.
IEEE COMMUNICATIONS LETTERS
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Jiexi Liu et al.
PRICAI 2019: TRENDS IN ARTIFICIAL INTELLIGENCE, PT III
(2019)
Article
Computer Science, Artificial Intelligence
Jingming Xue et al.
Article
Computer Science, Artificial Intelligence
Klaus Greff et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2017)
Article
Automation & Control Systems
Guo-Bing Zhou et al.
INTERNATIONAL JOURNAL OF AUTOMATION AND COMPUTING
(2016)
Article
Computer Science, Artificial Intelligence
Jun Ma et al.
Article
Multidisciplinary Sciences
S. Roberts et al.
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES
(2013)
