Using Deep Learning Techniques in Forecasting Stock Markets by Hybrid Data with Multilingual Sentiment Analysis

Electronics, Journal Year: 2022, Volume and Issue: 11(21), P. 3513 - 3513

Published: Oct. 28, 2022

Electronic word-of-mouth data on social media influences stock trading and the confidence of markets. Thus, sentiment analysis comments related to markets becomes crucial in forecasting However, current is mainly English. Therefore, this study performs multilingual by translating non-native English-speaking countries’ texts into This used unstructured from structured data, including technical indicators, forecast Deep learning techniques machine models have emerged as powerful ways coping with problems, parameter determination greatly models’ performance. Long Short-Term Memory (LSTM) employing genetic algorithm (GA) select parameters for predicting market indices prices company stocks hybrid regions. Numerical results revealed that developed LSTMGA model generates more accurate than other various types. proposed a feasible promising way market.

Language: Английский

---

Cluster-based industrial KPIs forecasting considering the periodicity and holiday effect using LSTM network and MSVR

Advanced Engineering Informatics, Journal Year: 2023, Volume and Issue: 56, P. 101916 - 101916

Published: March 6, 2023

Language: Английский

---

Artificial intelligence and digital twins in power systems: Trends, synergies and opportunities

Digital Twin, Journal Year: 2023, Volume and Issue: 2, P. 11 - 11

Published: March 13, 2023

Artificial Intelligence (AI) promises solutions to the challenges raised by digitalization of power grids and their assets. Decision-making, forecasting even operational optimization assets are just some that AI algorithms can provide operators, utilities vendors. Nevertheless, barriers such as access quality datasets, interpretability, repeatability, availability computational resources currently limit extent practical implementations. At same time, Digital Twins (DTs) foreseen platforms overcome these barriers, also a new environment for development enhanced more intelligent applications. In this manuscript, we review published literature determine existing capabilities implementation in systems, classify AI-based applications based on time scale reveal temporal sensitivity. Furthermore, DT-based technologies discussed, identifying potentials tackle current limitations real-world well exploring synergies between DTs AI. By combining DT, outline multiple prospective use cases AI-enhanced grid asset DTs. Our identifies combination leverages with potential fundamentally change aspects industry.

Language: Английский

---

Hierarchical temporal transformer network for tool wear state recognition

Advanced Engineering Informatics, Journal Year: 2023, Volume and Issue: 58, P. 102218 - 102218

Published: Oct. 1, 2023

Language: Английский

---

Multiple households energy consumption forecasting using consistent modeling with privacy preservation

Advanced Engineering Informatics, Journal Year: 2023, Volume and Issue: 55, P. 101846 - 101846

Published: Jan. 1, 2023

Language: Английский

---