Article
Computer Science, Theory & Methods
Michael Nair, Mohamed I. Marie, Laila A. Abd-Elmegid
Summary: Bitcoin is a significant and widely used cryptocurrency, and forecasting its price accurately is crucial for investors and academics. Research suggests that deep learning methods, particularly LSTM, outperform other approaches in predicting the price of Bitcoin.
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Chao Zhong, Wei Du, Wei Xu, Qianhui Huang, Yinuo Zhao, Mingming Wang
Summary: In this study, a novel end-to-end model is proposed for predicting the price trend of cryptocurrencies using long short-term memory (LSTM) and relationwise graph attention network (ReGAT). By considering both individual cryptocurrency features and their relationships, our model achieves effective price trend prediction and is validated using real-world cryptocurrency market data.
DECISION SUPPORT SYSTEMS
(2023)
Article
Computer Science, Information Systems
M. Poongodi, Tu N. Nguyen, Mounir Hamdi, Korhan Cengiz
Summary: This study aims to predict the price fluctuations of crypto-currencies by analyzing social media communication data and exploring the relationship between price variations and social media activities. The findings help us better understand the crypto currency ecosystems and provide insights for real-time trading systems.
INFORMATION PROCESSING & MANAGEMENT
(2021)
Article
Business
Sabri Boubaker, Sitara Karim, Muhammad Abubakr Naeem, Molla Ramizur Rahman
Summary: The role of big data in finance is crucial, especially in predicting stock prices, reducing risk, and evaluating market anomalies. This study estimates the systemic risk tolerance of twenty-five high-valued cryptocurrencies and finds valuable insights. It also develops a predictive model that can assist investors and market participants in adapting to market fluctuations.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2024)
Article
Computer Science, Artificial Intelligence
Navid Parvini, Mahsa Abdollahi, Sattar Seifollahi, Davood Ahmadian
Summary: Investigating different predictors for Bitcoin price forecasting, this study proposes a two-stage forecasting method and analyzes the profitability of the predictors through simulated trading experiments. The results show that Gold and Oil have the highest statistical accuracy in predicting Bitcoin returns, while S&P500 is the most profitable predictor.
APPLIED SOFT COMPUTING
(2022)
Article
Engineering, Marine
Yuchao Wang, Hui Wang, Bin Zhou, Huixuan Fu
Summary: Research on ship roll prediction methods based on deep learning, proposing single input single output and multiple input single output methods, analyzing and testing with real data to verify the accuracy and effectiveness of the models.
Article
Computer Science, Artificial Intelligence
SangEun Lee, Dahye Jeong, Eunil Park
Summary: Emojis have become a new tool for visual and linguistic expression on social media, allowing users to convey emotions and communicate with each other. To predict the most likely emojis within a text, a new deep neural network model called MultiEmo (multi-task framework for emoji prediction) is proposed, which considers the emotion detection task. Experimental results on the Twitter dataset show that MultiEmo outperforms existing models, indicating its ability to learn richer representations from semantically related tasks. New evaluation metrics are also introduced to measure the comprehensive performance of the models.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Milad Keshtkar Langeroudi, Mohammad Reza Yamaghani, Siavash Khodaparast
Summary: The main issue in time-series prediction is uncertainty, which this study addresses by proposing a deep fuzzy LSTM architecture. Experimental results demonstrate the superior performance of the proposed fuzzy-deep model in predicting various types of time series.
IEEE INTELLIGENT SYSTEMS
(2022)
Article
Biochemistry & Molecular Biology
Mohammed Aly, Abdullah Shawan Alotaibi
Summary: Deep learning has made significant contributions to drug research, particularly in predicting the properties of modified gedunin molecules. AI and ML technologies have the potential to improve rational drug design and exploration.
Article
Computer Science, Interdisciplinary Applications
Jun-Ho Kim, Hanul Sung
Summary: This paper analyzes the use of machine learning to predict bitcoin price. It addresses the challenge of impractical cost of hyperparameter optimization and proposes a method to identify the optimal hyperparameter combination. By analyzing prediction performance under different hyperparameter configurations, the paper highlights the importance of selecting distinct configurations based on the similarity between learning data and future data.
Article
Engineering, Marine
Farbod Farhangi, Abolghasem Sadeghi-Niaraki, Jalal Safari Bazargani, Seyed Vahid Razavi-Termeh, Dildar Hussain, Soo-Mi Choi
Summary: Sea surface temperature (SST) is crucial and predicting it accurately is of paramount importance. This paper used multiple features and deep neural network models to predict time-series hourly SST. Air pressure and water temperature were found to be more important than wind direction and wind speed. The proposed method showed low prediction errors and CNN was considered the most suitable model due to its fast training speed. The findings emphasize the importance of feature selection and the potential impact of variant features on prediction accuracy.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Multidisciplinary Sciences
Keshab Raj Dahal, Nawa Raj Pokhrel, Santosh Gaire, Sharad Mahatara, Rajendra P. Joshi, Ankrit Gupta, Huta R. Banjade, Jeorge Joshi
Summary: The accelerated progress in artificial intelligence has encouraged the use of advanced deep learning methods to predict stock prices. The easy accessibility of the stock market has made its behavior more fuzzy, volatile, and complex. This study fills the research gap in accurately predicting a target stock's closing price by incorporating financial news data with stock features, and the experimental results show that incorporating financial news data improves the prediction accuracy.
Article
Business, Finance
Zhuyi Shen, Shibo Wang, Jinqiang Yang
Summary: This research utilizes the Pareto distribution to model transaction types in the dynamic digital platform adoption and valuation theory. By deriving closed-form solutions, the paper establishes the analytical condition for determining whether the tokenized economy exhibits faster adoption than the numeraire economy. The study generalizes the conclusion of Cong et al. (2021) that user adoption is faster in a tokenized economy due to endogenous appreciation expectation, based on numerical analysis. Conversely, when the volatility effect of platform productivity exceeds the growth effect, the adoption rate of the tokenized platform slows down due to depreciation expectation.
FINANCE RESEARCH LETTERS
(2023)
Article
Chemistry, Analytical
Zeinab Shahbazi, Yung-Cheol Byun
Summary: The popularity of cryptocurrency has attracted attention in the academic field. In this study, the XGBoost algorithm and blockchain framework were used to predict the exchange rate, enhancing system security and transparency.
Article
Automation & Control Systems
Mohamed Sayah, Djillali Guebli, Zeina Al Masry, Noureddine Zerhouni
Summary: This paper proposes a framework to test the robustness of deep LSTM architecture for RUL prediction, and validates its resilience through the use of stress functions. The comparison between mutant fuzzed Deep LSTM networks and the original model indicates the quality of the RUL prediction model. The use of phi-stress operators demonstrates the ability to build stable and data-independent Deep LSTM models for RUL prediction.
Article
Computer Science, Interdisciplinary Applications
Lizhe Wang, Marcel Kunze, Jie Tao, Gregor von Laszewski
ADVANCES IN ENGINEERING SOFTWARE
(2011)
Article
Computer Science, Software Engineering
Gregor von Laszewski, Jai Dayal, Lizhe Wang
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2011)
Article
Computer Science, Software Engineering
Thomas R. Furlani, Matthew D. Jones, Steven M. Gallo, Andrew E. Bruno, Charng-Da Lu, Amin Ghadersohi, Ryan J. Gentner, Abani Patra, Robert L. DeLeon, Gregor von Laszewski, Fugang Wang, Ann Zimmerman
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2013)
Article
Computer Science, Interdisciplinary Applications
Lizhe Wang, Gregor von Laszewski, Fang Huang, Jai Dayal, Tom Frulani, Geoffrey Fox
ENGINEERING WITH COMPUTERS
(2011)
Article
Computer Science, Cybernetics
Lizhe Wang, Gregor von Laszewski, Dan Chen, Jie Tao, Marcel Kunze
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMS AND HUMANS
(2010)
Article
Computer Science, Information Systems
Lizhe Wang, Gregor von Laszewski, Jie Tao, Marcel Kunze
INTERNATIONAL JOURNAL OF AD HOC AND UBIQUITOUS COMPUTING
(2010)
Article
Computer Science, Hardware & Architecture
Lizhe Wang, Tobias Kurze, Jie Tao, Marcel Kunze, Gregor von Laszewski
JOURNAL OF SUPERCOMPUTING
(2013)
Article
Computer Science, Hardware & Architecture
Lizhe Wang, Gregor von Laszewski, Andrew Younge, Xi He, Marcel Kunze, Jie Tao, Cheng Fu
NEW GENERATION COMPUTING
(2010)
Article
Computer Science, Theory & Methods
Niranda Perera, Arup Kumar Sarker, Mills Staylor, Gregor von Laszewski, Kaiying Shan, Supun Kamburugamuve, Chathura Widanage, Vibhatha Abeykoon, Thejaka Amila Kanewela, Geoffrey Fox
Summary: The Data Science domain has witnessed significant expansion in the past decade, driven largely by the Big Data revolution. The use of Artificial Intelligence (AI) and Machine Learning (ML) in data engineering applications has led to the integration of data processing pipelines for terabytes of data. However, the commonly used serial Dataframes (e.g., R, pandas) face performance limitations when working with moderately large datasets. This paper introduces a cost model for evaluating parallel processing patterns and evaluates the performance of Cylon on the ORNL Summit supercomputer.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Information Systems
Vibhatha Abeykoon, Supun Kamburugamuve, Chathura Widanage, Niranda Perera, Ahmet Uyar, Thejaka Amila Kanewala, Gregor von Laszewski, Geoffrey Fox
Summary: Data-intensive applications are increasingly common in various scientific fields. The proposed HPTMT architecture provides an efficient way to create these applications, integrating various aspects of data engineering and data science, and proposing a system architecture that is better suited for high-performance computing environments.
FRONTIERS IN BIG DATA
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Vibhatha Abeykoon, Supun Kamburugamuve, Kannan Govindrarajan, Pulasthi Wickramasinghe, Chathura Widanage, Niranda Perera, Ahmet Uyar, Gurhan Gunduz, Selahattin Akkas, Gregor Von Laszewski
2019 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA)
(2019)
Proceedings Paper
Computer Science, Information Systems
Rick Wagner, Philip Papadopoulos, Dmitry Mishin, Trevor Cooper, Mahidhar Tatineti, Gregor von Laszewski, Fugang Wang, Geoffrey C. Fox
PROCEEDINGS OF XSEDE16: DIVERSITY, BIG DATA, AND SCIENCE AT SCALE
(2016)
Proceedings Paper
Computer Science, Information Systems
Lizhe Wang, Gregor von Laszewski, Marcel Kunze, Jie Tao
2010 24TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED INFORMATION NETWORKING AND APPLICATIONS (AINA)
(2010)