Article
Computer Science, Information Systems
Nishant Jagannath, Tudor Barbulescu, Karam M. Sallam, Ibrahim Elgendi, Asuquo A. Okon, Braden Mcgrath, Abbas Jamalipour, Kumudu Munasinghe
Summary: This paper introduces on-chain metrics derived from data on the Bitcoin network to predict the price of Bitcoin using a deep learning model and a self-adaptive technique. Compared to traditional LSTM model, this approach offers higher accuracy and lower error rates.
Article
Computer Science, Artificial Intelligence
Shahab Rajabi, Pardis Roozkhosh, Nasser Motahari Farimani
Summary: This paper presents a method for Bitcoin price prediction based on neural networks and introduces a new approach called Learnable Window Size. By implementing two-level deep neural networks, the best window size and Bitcoin price are predicted based on the observed price trend and fluctuations. Evaluations show that this method achieves lower errors in terms of the prediction hardship factor.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Theory & Methods
Shengmin Xu, Jianting Ning, Jinhua Ma, Xinyi Huang, Robert H. Deng
Summary: Blockchain, as an immutable and append-only distributed ledger, faces challenges when dealing with illegal content and data modification requirements. Researchers propose a new notion called K-time modifiable and epoch-based redactable blockchain with a monetary penalty to control rewriting and penalize malicious behaviors.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2021)
Article
Economics
Crina Anina Bejan, Dominic Bucerzan, Mihaela Daciana Craciun
Summary: This study investigates the relationship between Bitcoin price evolution and energy consumption tendency and finds a strong correlation between them.
Article
Computer Science, Information Systems
Liang Du, Ruobin Gao, Ponnuthurai Nagaratnam Suganthan, David Z. W. Wang
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)
Article
Business, Finance
Anantha Divakaruni, Peter Zimmerman
Summary: The Lightning Network allows for Bitcoin payments to be made off the blockchain, resulting in reduced congestion and increased efficiency. Our study reveals that this improvement cannot be accounted for by other factors and the impact of centralization on efficiency remains inconclusive. These findings have implications for the future of cryptocurrencies as a payment method and their environmental impact.
FINANCE RESEARCH LETTERS
(2023)
Article
Engineering, Environmental
Yueyan Li, Jiaqi Chen, Hancheng Dan, Hao Wang
Summary: A prediction model for evaluating the probability distribution of pavement surface temperature in winter was developed and validated, consisting of a Bayesian Structural Time Series module and a Bayesian Neural Network module. Results showed that the majority of measured pavement temperatures fell within the predicted 95% confidence interval, indicating reliability. Different components of the model had varying influences on the prediction results.
COLD REGIONS SCIENCE AND TECHNOLOGY
(2022)
Article
Multidisciplinary Sciences
Yulin Liu, Luyao Zhang, Yinhong Zhao
Summary: This study applies cohort analysis to interpret Bitcoin blockchain data in a more efficient and economically insightful way. By querying and processing the Bitcoin transaction input and output data within each daily cohort, we are able to derive key Bitcoin transaction indicators and create datasets and visualizations accordingly.
Article
Computer Science, Theory & Methods
Maruf Monem, Md Tamjid Hossain, Md. Golam Rabiul Alam, Md. Shirajum Munir, Md. Mahbubur Rahman, Salman A. AlQahtani, Samah Almutlaq, Mohammad Mehedi Hassan
Summary: Bitcoin, the largest cryptocurrency, faces challenges in broader adaption due to long verification times and high transaction fees. To tackle these issues, researchers propose a learning framework that uses machine learning to predict the ideal block size in each block generation cycle. This model significantly improves the block size, transaction fees, and transaction approval rate of Bitcoin, addressing the long wait time and broader adaption problem.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Article
Business, Finance
Michael L. Polemis, Mike G. Tsionas
Summary: In recent years, there has been a growing concern about the environmental impact of Bitcoin usage. This study uses Bayesian analysis and quantile cointegrated vector autoregression to investigate the factors that contribute to the carbon footprint of Bitcoin.
INTERNATIONAL JOURNAL OF FINANCE & ECONOMICS
(2023)
Article
Mathematics, Interdisciplinary Applications
Alberto Partida, Saki Gerassis, Regino Criado, Miguel Romance, Eduardo Giraldez, Javier Taboada
Summary: This article examines the structure of the daily price volatility time series of Bitcoin and Ethereum, confirming their chaoticity, long-term correlation, and multifractality. It also analyzes the corresponding visibility graphs and complex networks, validating the fractality of the original time series and the lack of uncorrelated randomness in the price series.
CHAOS SOLITONS & FRACTALS
(2022)
Article
Mathematics
Roland Bolboaca, Piroska Haller
Summary: This paper examines the impact of hyperparameters on long short-term memory neural networks and their prediction performance. It demonstrates the effect of each tested hyperparameter on the training and testing procedures by conducting over 100,000 experiments. The study also explores the applicability of a modified teacher forcing approach in a process state monitoring system.
Article
Computer Science, Artificial Intelligence
Wenjie Du, David Cote, Yan Liu
Summary: This paper proposes SAITS, a novel method based on the self-attention mechanism, for missing value imputation in multivariate time series. SAITS is trained using a joint-optimization approach and learns missing values from a weighted combination of two diagonally-masked self-attention (DMSA) blocks. The DMSA blocks capture temporal dependencies and feature correlations, improving imputation accuracy and training speed.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Interdisciplinary Applications
Enrico Longato, Mario Luca Morieri, Giovanni Sparacino, Barbara Di Camillo, Annamaria Cattelan, Sara Lo Menzo, Marco Trevenzoli, Andrea Vianello, Gabriella Guarnieri, Federico Lionello, Angelo Avogaro, Paola Fioretto, Roberto Vettor, Gian Paolo Fadini
Summary: This study utilizes dynamic Bayesian networks and prototyping to integrate data analysis, allowing for the visualization of patient trajectories in COVID-19 outcomes, which could guide timely and appropriate clinical decisions.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Chemistry, Analytical
Alexandre Augusto Giron, Jean Everson Martina, Ricardo Custodio
Summary: Steganography, a method of hiding data between parties, has been suggested to be potentially used in public blockchains for hiding communications, although concrete evidence of actual use is lacking. Researchers have developed a steganalysis approach for Bitcoin and Ethereum to investigate the presence of steganography in these cryptocurrencies.