Residual long short-term memory network with multi-source and multi-frequency information fusion: An application to China?s stock market

Article Computer Science, Hardware & Architecture

Stock-Price Forecasting Based on XGBoost and LSTM

Pham Hoang Vuong et al.

Summary: This article presents a method that uses machine learning and deep learning approaches for stock price forecasting. The study demonstrates that this method outperforms traditional approaches in feature extraction and price prediction.

COMPUTER SYSTEMS SCIENCE AND ENGINEERING (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Multi-task short-term reactive and active load forecasting method based on attention-LSTM model

Jiaqi Qin et al.

Summary: In this paper, a novel multi-task load forecasting method is proposed using LSTM architecture and attention mechanism to predict both active and reactive power loads simultaneously. With multi-task regression based on hard parameter sharing and adaptive combined task-wise loss function, the proposed method optimizes forecasting accuracy for both types of loads. The results demonstrate the robustness and reliability of the proposed multi-task load forecasting model in practical power system applications.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2022)

Add to Collection

Article Computer Science, Information Systems

Bayesian optimization based dynamic ensemble for time series forecasting

Liang Du et al.

Summary: In this paper, a Bayesian optimization-based dynamic ensemble (BODE) method is proposed for time series forecasting. The BODE method combines ten different model candidates and uses a model-based Bayesian optimization algorithm for combination hyperparameter tuning. The method demonstrates robust performance and better generalization capability.

INFORMATION SCIENCES (2022)

Add to Collection

Article Computer Science, Information Systems

Multivariable time series forecasting using model fusion

Ruijin Wang et al.

Summary: This paper proposes a model fusion-based time series forecasting method to improve the accuracy and efficiency of predictions using multivariate grey model and artificial fish swarm algorithm. Two fusion models based on data decomposition and weighted summation achieve good prediction results in different scenarios.

INFORMATION SCIENCES (2022)

Add to Collection

Article Computer Science, Information Systems

An ensemble of a boosted hybrid of deep learning models and technical analysis for forecasting stock prices

Amadu Fullah Kamara et al.

Summary: This study proposes a brand-new algorithm EHTS for stock price forecasting, which outperforms baseline schemes in experiments. By utilizing deep learning and various metrics for stock price prediction, short-term trading opportunities are identified.

INFORMATION SCIENCES (2022)

Add to Collection

Article Engineering, Civil

Key Points Estimation and Point Instance Segmentation Approach for Lane Detection

Yeongmin Ko et al.

Summary: The proposed traffic line detection method, PINet, based on key points estimation and instance segmentation, is adaptive to various environments and computing power. PINet allows for choosing the size of trained models based on the target environment's computing power, achieving competitive accuracy and false positive rates on popular public datasets like CULane and TuSimple.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Add to Collection

Article Computer Science, Information Systems

Poly-linear regression with augmented long short term memory neural network: Predicting time series data

Supriyo Ahmed et al.

Summary: The supply chain sector has undergone a rapid digital transformation, incorporating AI, machine learning, and data science technology to replace outdated methods. Researchers have proposed a novel deep learning approach that can accurately predict future financial markets. Experimental validations demonstrate that this method outperforms other machine learning and deep learning approaches on several datasets.

INFORMATION SCIENCES (2022)

Add to Collection

Article Computer Science, Information Systems

DA-Net: Dual-attention network for multivariate time series classification

Rongjun Chen et al.

Summary: In this paper, a novel network called DA-Net is proposed for mining local-global features in multivariate time series classification. DA-Net consists of two layers, the Squeeze-Excitation Window Attention (SEWA) layer and the Sparse Self-Attention within Windows (SSAW) layer, which capture local and global features and mine critical local sequence fragments through establishing global long-range dependencies.

INFORMATION SCIENCES (2022)

Add to Collection

Article Computer Science, Information Systems

Novel hybrid multi-head self-attention and multifractal algorithm for non-stationary time series prediction

Xiang Yu et al.

Summary: This study proposes a novel dynamic recurrent neural network for stable and robust prediction of non-stationary multivariate time series. By extracting volatility characteristics and introducing a self-attention mechanism, the proposed model outperforms traditional methods in experiments.

INFORMATION SCIENCES (2022)

Add to Collection

Article Computer Science, Information Systems

Mining relevant partial periodic pattern of multi-source time series data

Yaling Xun et al.

Summary: Traditional partial periodic pattern mining algorithms tend to work on a single time series or database. This article proposes a new pattern-relevant partial periodic patterns and its mining algorithm, which can effectively reflect and mine the correlations of multi-source time series data. The algorithm quickly identifies important patterns by introducing the contribution difference of various patterns, and utilizes an improved mining algorithm to obtain frequent partial periodic patterns. Experimental results demonstrate the effectiveness of the algorithm in sparse databases.

INFORMATION SCIENCES (2022)

Add to Collection

Article Computer Science, Information Systems

Stock Prediction Based on Technical Indicators Using Deep Learning Model

Manish Agrawal et al.

Summary: This study develops an Evolutionary Deep Learning Model (EDLM) to identify stock trends' prices by utilizing Stock Technical Indicators (STIs) and deep learning models. The proposed model shows significant improvements in stock market trend prediction and aids investors in making profitable investment decisions.

CMC-COMPUTERS MATERIALS & CONTINUA (2022)

Add to Collection

Article Mathematics

Forecasting Stock Market Volatility Using Hybrid of Adaptive Network of Fuzzy Inference System and Wavelet Functions

Abdullah H. Alenezy et al.

Summary: This study models and enhances the forecasting accuracy of Saudi Arabia's stock exchange data patterns using the MODWT-LA8-ANFIS model with input variables of oil prices and repo rates. The performance of the model surpasses traditional models, making it suitable for stock market analysis and prediction.

JOURNAL OF MATHEMATICS (2021)

Add to Collection

Article Computer Science, Information Systems

Attention enhanced long short-term memory network with multi-source heterogeneous information fusion: An application to BGI Genomics

Qun Zhang et al.

Summary: This study presents an analytical framework based on multiple data sources, demonstrates the prediction of BGI Genomics stock price, and applies an LSTM network, showing that performance can be significantly improved through multisource information fusion.

INFORMATION SCIENCES (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Res2Net: A New Multi-Scale Backbone Architecture

Shang-Hua Gao et al.

Summary: This paper introduces a novel building block for CNNs, Res2Net, which represents multiscale features within one single residual block by constructing hierarchical residual-like connections. The Res2Net enhances the representation of multiscale features in various vision tasks and consistently outperforms baseline models in performance gains.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

TRk-CNN: Transferable Ranking-CNN for image classification of glaucoma, glaucoma suspect, and normal eyes

Tae Joon Jun et al.

Summary: This paper introduces a Transferable Ranking Convolutional Neural Network (TRk-CNN) for effectively handling the highly correlated classes in image classification. By combining weights of primitive classification models, TRk-CNN reflects inter-class information to the final classification phase, showing superior performance in terms of accuracy and sensitivity on a glaucoma fundus image dataset compared to other models.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

Add to Collection

Article Computer Science, Information Systems

An interpretable Neural Fuzzy Hammerstein-Wiener network for stock price prediction

Chen Xie et al.

Summary: This paper proposes an interpretable regression model for stock price prediction, which integrates a neuro-fuzzy system with the Hammerstein Wiener model. Experimental results show that the proposed Neural Fuzzy Hammerstein-Wiener (NFHW) outperforms other neuro-fuzzy systems and the conventional Hammerstein-Wiener model in stock price prediction.

INFORMATION SCIENCES (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Improving abstractive summarization based on dynamic residual network with reinforce dependency

Weizhi Liao et al.

Summary: A new encoder-decoder model based on dynamic residual network is proposed in this work to improve LSTM's long sequence dependencies by dynamically selecting an optimal state and simulating word dependence using reinforcement learning. Experimental results demonstrate significant improvements in capturing long-term dependencies compared to traditional LSTM-based Seq2Seq abstractive summarization model.

NEUROCOMPUTING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Stock price prediction using deep learning and frequency decomposition

Hadi Rezaei et al.

Summary: The combination of new deep learning and decomposition algorithms has improved the accuracy and performance of financial time series analysis. Combining CEEMD with CNN and LSTM can produce better prediction results.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

Add to Collection

Article Computer Science, Information Systems

A novel graph convolutional feature based convolutional neural network for stock trend prediction

Wei Chen et al.

Summary: The paper introduces a novel method for stock trend prediction using GC-CNN model, which considers both stock market information and individual stock information. Experimental analysis demonstrates that the proposed method outperforms several stock trend prediction methods and stock trading strategies.

INFORMATION SCIENCES (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

A fast evidential approach for stock forecasting

Tianxiang Zhan et al.

Summary: This paper explores the fusion method of evidence theory to improve the accuracy of stock price prediction, with a focus on time series data, and emphasizes the advantage of fast processing speed.

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS (2021)

Add to Collection

Article Automation & Control Systems

Short-Term Stock Price Forecasting Based on an SVD-LSTM Model

Mei Sun et al.

Summary: This study proposes a model for predicting stock prices using singular value decomposition and long short-term memory model, which can improve prediction accuracy. Experimental results show that the proposed method can effectively enhance the accuracy of stock price predictions.

INTELLIGENT AUTOMATION AND SOFT COMPUTING (2021)

Add to Collection

Article Business, Finance

Systemic financial risk early warning of financial market in China using Attention-LSTM model

Zi-sheng Ouyang et al.

Summary: The study found that network public opinion has a non-linear Granger causality with systemic risk, the Attention-LSTM neural network model has strong generalization ability, and it has a higher accuracy rate compared to other models.

NORTH AMERICAN JOURNAL OF ECONOMICS AND FINANCE (2021)

Add to Collection

Article Computer Science, Hardware & Architecture