Peter T. Yamak, Yujian Li, Ting Zhang, Pius Kwao Gadosey
In this paper, we introduce Wide-TSNet, a novel hybrid approach for predicting Bitcoin prices using time-series data transformed into images. The method involves converting time-series data into Markov transition fields (MTFs), enhancing them using histogram equalization, and classifying them using Wide ResNets, a type of convolutional neural network (CNN). We propose a tripartite classification system to accurately represent Bitcoin price trends. In addition, we demonstrate the effectiveness of Wide-TSNet through various experiments, in which it achieves an Accuracy of approximately 94% and an F1 score of 90%. It is also shown that lightweight CNN models, such as SqueezeNet and EfficientNet, can be as effective as complex models under certain conditions. Furthermore, we investigate the efficacy of other image transformation methods, such as Gramian angular fields, in capturing the trends and volatility of Bitcoin prices and revealing patterns that are not visible in the raw data. Moreover, we assess the effect of image resolution on model performance, emphasizing the importance of this factor in image-based time-series classification. Our findings explore the intersection between finance, image processing, and deep learning, providing a robust methodology for financial time-series classification.
Currently bitcoin is considered an investment tools, the value of bitcoin itself is unstable so it is difficult to predict which can cause losses for bitcoin traders. Some previous research shows that Long Short-Term Memory (LSTM) which is a deep learning approach as an improvement of RNN has the best performance in predicting stocks and cryptocurrencies compared to Support Vector Machine (SVM), Exponential Moving Average (EMA), and Moving Average (MA), and Seasonal Autoregressive Integrated Moving Average (SARIMA). LSTM has the disadvantage that it is difficult to understand in determining the best parameters and to obtain good results it needs strict hyperparameter adjustment. This study aims to find the best parameters in LSTM by selecting the amount of data, training data composition, batch size, epoch and the amount of prediction time and analyzing prediction performance. In this study, data collection was carried out in real time and was able to provide predictions for the next few days. The test results of the LSTM algorithm have a performance with an average accuracy of 93.69% with the parameters of the amount of bitcoin price data used is 3 years, with a percentage of train data of 85%, using 10 batch sizes, with a number of epochs 125, and the highest average accuracy rate for 7 days of prediction.
In this paper, we performed bitcoin price prediction based on bitcoin price dataset using Support Vector Machine model, Random Forest model, Neural Network model, XGBoost model and LightGBM model and evaluated the performance of these models. We divided the Bitcoin price dataset into training and test sets in a ratio of 7:3, where 70 were used as the training set and 30 as the test set. The models were trained with the training set and tested with the test set using the stock price change (yield) as the target variable and other variables as input variables. By comparing the MSE, RMSE, MAE, MAPE and R² of the different models were evaluated and it was found that XGBoost has the best performance and the best prediction. The performance of the other four models ranged from good to poor, including LightGBM, Random Forest, Support Vector Machine and Neural Network. Among them, the neural network, whose MSE is tens of times higher than the other four models, performs the worst. The research results in this paper can provide reference value for future Bitcoin price prediction, and also provide some reference for choosing appropriate machine learning models.
This study provides a comprehensive analysis of the existing body of work on predicting the price of Bitcoin using deep learning techniques. It discusses the fundamental concepts behind deep learning and Bitcoin, including recurrent neural networks, convolutional neural networks, and long short-term memory networks. The study also examines the data sources used in training these models, including historical Blockchain transaction data, social media sentiments, and Bitcoin prices. The report also highlights the importance of metrics like mean absolute error, mean squared error, and root mean squared error for evaluating the effectiveness of various models. It also discusses future research topics, such as incorporating external factors into prediction models. The article offers valuable insights for academics, practitioners, and policymakers interested in cryptocurrency prediction.
Since cryptocurrencies are among the most extensively traded financial instruments globally, predicting their price has become a crucial topic for investors. Our dataset, which includes fluctuations in Bitcoin’s hourly prices from 15 May 2018 to 19 January 2024, was gathered from Crypto Data Download. It is made up of over 50,000 hourly data points that provide a detailed view of the price behavior of Bitcoin over a five-year period. In this study, we used potent algorithms, including gradient descent, attention mechanisms, long short-term memory (LSTM), and artificial neural networks (ANNs). Furthermore, to estimate the price of Bitcoin, we first merged two deep learning algorithms, LSTM and attention mechanisms, and then combined LSTM-Attention with gradient-specific optimization to increase our model’s performance. Then we integrated ANN-LSTM and included gradient-specific optimization for the same reason. Our results show that the hybrid model with gradient-specific optimization can be used to anticipate Bitcoin values with better accuracy. Indeed, the hybrid model combines the best features of both approaches, and gradient-specific optimization improves predictive performance through frequent analysis of pricing data changes.
Bitcoin has become a prominent financial instrument in recent years, attracting increasing attention as a digital currency. Accurately forecasting the valuation of a financial asset carries substantial significance for both retail and institutional investors. The aim of this study is to evaluate and compare the predictive capabilities of various models, namely Support Vector Regression (SVR), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), a hybrid model combining CNN and Bidirectional LSTM (CNN-BiLSTM), and XGBoost, in the context of forecasting Bitcoin price. The main aim of this study is to ascertain the algorithm that demonstrates the most efficacy in forecasting the price of Bitcoin. This study utilizes the S&P500 index, Gold/Dollar exchange rate, West Texas Spot Oil Price, and Dollar Index as exogenous factors in order to forecast the price of Bitcoin. The dataset encompasses a consecutive time span of 2191 days, commencing on January 1, 2015 and concluding on September 18, 2023. The models outlined in the study undergo a two-stage procedure, including of training and testing. The assessment of the models' performance was carried out by utilizing several statistical measures, such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R-squared (R2). The results indicate that the XGBoost algorithm had greater performance in projecting the price of Bitcoin, as evidenced by its consistently higher performance metrics across all evaluated aspects. The XGBoost model was succeeded by the CNN-BiLSTM, CNN, and LSTM models, which are hybrid methodologies, resulting in the most advantageous results. The SVR model demonstrated the least favorable performance..
Counterfeit products have become a significant problem for small and medium-sized businesses (SMBs), with the estimated value of counterfeit goods worldwide reaching trillions of dollars. However, SMBs often lack the resources and technical expertise to implement sophisticated anti-counterfeiting measures. Towards this end, the work proposes a blockchain-based solution named as Fake Product Identification for Small and Medium Firms (FPISMF) using Hyperledger and AES encryption to enable SMBs to identify fake products and protect their brand reputation. The details of the products and the details of customers are encrypted using AES encryption and recorded on the blockchain. The application communicates with the blockchain network to validate the product and retrieve the details of the product. Chaincode is executed in a containerized environment, which provides isolation and security for the code and data being processed. An algorithm is also proposed to substitute the missing QR-code bits and data that helps reduce customer wait time. Experiments are conducted on synthesized data sets and results showing the effectiveness of the proposed FPISMF framework and reconciliation technique. It is observed from the results that though the time taken to replace a blurry bit is greatly reduced as compared to manual replacement of the product, there is an increase in this time when associated with encryption while extraction of the corresponding code from cloud database thereby achieving a time complexity of O(n), where ‘n’ is the number of scanned products. In addition, the AES SMB time complexity is approximately recoded as O(n/2) and the Cloud access and retrieval time is O(n) as compared to O(2n) in the existing work. This shows a significant improvement in the ability to replace missing bits and perform a secure analysis respectively.
Open access
Blockchain Technology Applications and Security
Advanced Steganography and Watermarking Techniques
Block chain technology, non-fungible tokens (NFTs), and cryptocurrency have all contributed to the explosive rise of the digital assets sector. The dynamic and cutting-edge digital asset marketplace shown in this abstract is intended to satisfy the various demands of traders, investors, and enthusiasts in the digital asset market. The marketplace offers a user-friendly and safe platform for purchasing, selling, and managing different digital assets, and it is distinguished by its user-centric approach. It offers real-time market data, order book information, and robust analytical capabilities for well-informed decision-making, all with an intuitive interface that streamlines asset transactions. The ability to move assets seamlessly between blockchain networks, multi factor authentication, cold storage, and complex trading algorithms that optimise trading tactics are some of the key characteristics. ----------------------------------------------------------------------------------------------------------------------------------- Keywords Blockchain, Smart Contract, Ethereum, Transparency, Data sharing, Privacy, Byzantine fault tolerance, decentralized systems.
Technological advances in the last decades have led to the realization of the concept of a smart environment. A significant part of this development is decentralized ledger technology and its variant, a blockchain. The blockchain database is immutable, open to all stakeholders, secure by architecture and robust. Applying a blockchain in water supply sanitary control creates opportunities for optimization, higher quality of service, cost reduction, better sanitary standards and public control. Physical, chemical, and biological water supply contamination is a great source of public health hazards. Implementation of a blockchain for water supply IoT, from the source point to the consumption point, enables effective response to changing environments, possible cross-contamination, stormwater management or disaster and emergency action. The chapter encompasses all fundamental elements and principles of water collection, distribution and consumption, with a focus on the health hazards and sanitary requirements for potable water. The chapter listed the main contaminants, methods of their registration and elimination, and requirements for drinking water in accordance with WHO, EU Drinking Water Directive and EPA standards. Blockchain technology solutions are described for smart water supply, including smart supply management, smart contracts, tokenization, smart compliance systems, and, most importantly, effective utilization of distributed ledger technologies for sanitary monitoring of water sources, water treatment, and water distribution systems.
Cryptocurrency is a virtual currency that can be used as a financial or economic standard, foreign currency reserve, and as a means of payment in some countries. The value that goes up and down every time is not easy to predict using logic. This is a problem for investors, besides that investors lack knowledge about the direction of crypto money movement. In addition, there is no system that can predict the price of Bitcoin, so this can cause investors to take the wrong steps in transactions and can cause losses. To avoid this risk, a system is needed that can predict bitcoin prices using data mining techniques, namely forecasting, the algorithms used are CNN and LSTM. The data used is Bitcoin closing price data from January 1, 2017, to April 26, 2023. The data is divided into 80% training data and 20% testing data. The prediction results are evaluated using MAPE which gets a MAPE value of 0.037 or 3.7% in the CNN algorithm, while the LSTM algorithm gets a value of 0.065 or 6.5%. The MAPE results of the two algorithms are in the MAPE range <10%, so it can be said that the ability of the forecasting model is very good so that it can be used as a reference to determine the prediction of bitcoin prices in the next few periods.
Shimal Sh. Taher, Siddeeq Y. Ameen, Jihan A. Ahmed
Scalability remains a critical challenge for blockchain technology, limiting its potential for widespread adoption in high-demand transactional systems. This paper proposes an innovative solution to this challenge by applying the Snake Optimization Algorithm (SOA) to a blockchain framework, aimed at enhancing transaction throughput and reducing latency. A thorough literature review contextualizes our work within the current state of blockchain scalability efforts. We introduce a methodology that integrates SOA into the transaction validation process of a blockchain network. The effectiveness of this approach is empirically evaluated by comparing transaction processing times before and after the implementation of SOA. The results show a substantial reduction in latency, with the optimized system achieving lower average transaction times across various transaction volumes. Notably, the latency for processing batches of 10 and 100 transactions decreased from 30.29 ms to 155.66 ms–0.42 ms and 0.37 ms, respectively, post optimization. These findings indicate that SOA is exceptionally efficient in batch transaction scenarios, presenting an inverse scalability behavior that defies typical system performance degradation with increased load. Our research contributes a significant advancement in blockchain scalability, with implications for the development of more efficient and adaptable blockchain systems suitable for high throughput enterprise applications.
Open access
Blockchain Technology Applications and Security
Advanced Steganography and Watermarking Techniques
Kamal Kumar, Vinod Kumar, Seema, M. K. Sharma · 6 authors
Blockchain is a very secure, authentic, and distributed technology and is very prominent in areas such as edge computation, cloud computation, and Internet-of-things. Artificial intelligence assists in the completion of activities efficiently and effectively by providing intelligence, analytics, and predicting capabilities. There is an obvious convergence between the two technologies. Artificial intelligence systems can utilize blockchain to establish trust in communication channels, ensuring that messages are securely transmitted and received without the need for a centralized intermediary. By leveraging blockchain, artificial intelligence systems can maintain an immutable record of communications, ensuring transparency and preventing unauthorized modifications. The integration of blockchain and artificial intelligence technologies can enhance the security, transparency, and privacy of communication systems. By leveraging blockchain’s decentralized nature and artificial intelligence’s analytical capabilities, secure and trustworthy communication channels can be established, benefiting various domains such as finance, healthcare, and supply chain. Overall, the integration of blockchain and artificial intelligence has the potential to offer several benefits, and as these technologies continue to evolve, new and innovative applications will continue to emerge.
The rapid development of information technology, especially the Internet, has facilitated users with a quick and easy way to seek information. With these convenience offered by internet services, many individuals who initially invested in gold and precious metals are now shifting into digital investments in form of cryptocurrencies. However, investments in crypto coins are filled with uncertainties and fluctuation in daily basis. This risk posed as significant challenges for coin investors that could result in substantial investment losses. The uncertainty of the value of these crypto coins is a critical issue in the field of coin investment. Forecasting, is one of the methods used to predict the future value of these crypto coins. By utilizing the models of Long Short Term Memory, Support Vector Machine, and Polynomial Regression algorithm for forecasting, a performance comparison is conducted to determine which algorithm model is most suitable for predicting crypto currency prices. The mean square error is employed as a benchmark for the comparison. By applying those three constructed algorithm models, the Support Vector Machine uses a linear kernel to produce the smallest mean square error compared to the Long Short Term Memory and Polynomial Regression algorithm models, with a mean square error value of 0.02. Keywords: Cryptocurrency, Forecasting, Long Short Term Memory, Mean Square Error, Polynomial Regression, Support Vector Machine
Blockchain and Machine Learning (ML) are state-of-the-art technologies in the digital era. Developing countries have witnessed great digital transformation, and one of the key challenges during this development phase has been to create a platform that integrates the health and vitals of citizens confidentially. The healthcare insurance industry is one sector that has experienced a significant number of instances of fraudulent claims and mismanagement of patient data. These issues often arise due to inadequate technological integration and an over-reliance on manual processes and human intervention. The insurance industry relies on multiple processes between end users to initiate, maintain, and close diverse policies. The proposed model initially recommends a suitable insurance policy for newly admitted patients, but in the case of existing patients, the objectives are to speed up transaction processing and payment settlement securely using a private blockchain. Collectively, these two technologies possess the potential to revolutionize the future. This study aims to incorporate blockchain and ML techniques like Support Vector Machine (SVM) and Random Forest Regression, which can differentiate between fraudulent and legal medical records to recommend personalized policies, streamline claim processing, and ensure the security of sensitive patient information and vital insurance records. The key aim is to create a more patient-centric environment with data transparency. This integrated framework results in a secure, adaptable, and efficient ecosystem that outperforms traditional methods, paving the way for the future of healthcare and insurance services.
Econometrics can be used to understand and forecast price movements, assess market efficiency, and explore the factors influencing Bitcoin's value and adaptation. Econometrics is related to bitcoin in seven categories: price analysis and prediction, market efficiency, determination of Bitcoin prices, risk analysis, adaptation and network effects, causality tests, and simulation and stress. Testing these analyses can be invaluable for policymakers, investors, and financial institutions interested in the economics of digital currencies. Bitcoin price prediction in machine learning has many challenges that have deep roots in 2 main properties: cryptocurrencies and complexities in the Machine Learning models. Many problems are associated with machine learning for bitcoin price prediction, such as overfitting, data quality and availability, latent variables, model interpretability, computational complexity, dynamic adaptation, market manipulation, anomalies, data snooping bias risk, and time horizon mismatch. In the paper, we proposed an efficient framework for the prediction of bitcoin using nine different machine learning algorithms (linear Regression, random forest, adaboost, tree, KNN, gradient boosting, constant, neural network, SVM) on five different datasets. The results revealed that linear Regression emerged as the optimal model for the first data set. In the second data set, the random forest model demonstrated superior performance. The third data set exhibited the highest efficacy when the Adaboost model was employed. The fourth data set yielded the best outcomes with the random forest model, while linear Regression was the most effective choice for the final data set.
Bitcoin’s daily value fluctuations are very dynamic. Understanding its rapid and intricate price movements demands advanced techniques for processing complex data. This research aims to compare the accuracy of two machine learning methods, Random Forest (RF) and Long Short-Term Memory (LSTM), in predicting Bitcoin price. This research employs RF and LSTM algorithms to forecast Bitcoin prices using a two-year Yahoo Finance dataset. The evaluation metrics used were accuracy based on Mean Absolute Percentage Error (MAPE) and computational power (CPU-Z). As a result of this research, the LSTM model demonstrates higher accuracy compared to the RF model. MAPE reveals LSTM’s precision of 99.8% and RF’s accuracy of 90.1%. Regarding computational time and resources, RF shows slightly better performance than LSTM. The visual comparison further emphasizes LSTM’s better performance in predicting Bitcoin prices, highlighting its potential for informed decision-making in cryptocurrency trading. This research contributes valuable insights into the effectiveness, strengths, and weaknesses of LSTM and RF models in predicting cryptocurrency trends.
As Deep Learning (DL) continues to be widely adopted, the growing field of study on the robustness of DL approaches in finance is gaining steam. This paper investigates the robustness of a Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) intended for daily closing price predictions of Bitcoin (BTC). The research entails reproducing and adjusting an LSTM design from previous research, with an emphasis on evaluating the robustness of the network. The network is trained using data that has been disturbed by Gaussian noise to assess robustness, and the effect on predictions made outside of the sample is examined. To examine the impact of adding Gaussian noise layers and noisy dense layers on training accuracy and out-of-sample predictions, further robustness tests are conducted. The results show that the LSTM network has remarkable robustness to random disturbances in the data. Nevertheless, the Root Mean Square Error (RMSE) of the prediction increases with the addition of Gaussian noise and noisy dense layers. When random noise is present in the training data, the Autoregressive Integrated Moving Average (ARIMA) model is more vulnerable to it than the LSTM, according to the robustness of the two models. These findings highlight how robustness DL techniques are overall when compared to more conventional linear methods. However, because these models are black-box, the study highlights the significance of comprehensive testing. Although the robustness of the LSTM is impressive, it is important to understand that each network may behave differently depending on the circumstances.
Abstract: With the help of specific factors, this effort seeks to improve the present analysis of bitcoin and forecast its price. After conducting a thorough investigation, it was determined which factors all contribute to daily fluctuations in the value of bitcoin. All of the data in this work is made up of various aspects from daily records from the previous few years. The first step in this endeavour is gathering all the data necessary to forecast the price of bitcoin. All of the data was compiled during the previous few years, and it was incorporated into this work. The Recurrent neural network (RNN) algorithm is employed in this work because it provides significantly improved accuracy than earlier techniques. In order for investors to invest in bitcoin easily and for beginners to this market or business, this study forecasts signs of change in the price of the cryptocurrency.
Financial anomalies must be detected in order for financial institutions and regulatory bodies to manage risks and avoid fraudulent behavior. Financial anomaly detection is the practice of identifying unexpected or irregular financial transactions or patterns that may indicate fraudulent behavior or errors. It is crucial in today's digital era to prevent fraud, limit financial losses, and maintain secure financial systems. Various types of financial anomalies, such as credit card fraud, money laundering, financial statement fraud, and cryptocurrency fraud, pose significant risks to individuals and organizations. This review critically evaluates a selected research article on the use of blockchain technology in conjunction with data mining techniques to detect financial anomalies. The paper employs the case study method to demonstrate how well the suggested integrated system works in spotting financial anomalies. This review evaluates the article's methodology and conclusions and discusses its implications for practice. The report claims that merging data mining methods with blockchain technology can increase the precision and effectiveness of financial anomaly identification. This research advances knowledge about how block-chain technology and data mining techniques can be used to find financial abnormalities while also offering suggestions for further study and use.
This study aims to find the best performing model in predicting cryptocurrencies using different machine learning models. In our study, an analysis was performed on various cryptocurrencies such as Aave, BinanceCoin, Bitcoin, Cardano, Cosmos, Dogecoin, Ethereum, Solana, Tether, Tron, USDCoin and XRP. Decision Trees, Random Forests, KNearest Neighbours (KNN), Gradient Boost Machine (GBM), LightGBM, XGBoost, CatBoost, Artificial Neural Networks (ANN), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs) and Short Term Memory networks in Long Comparisons (LSTM) models were used. The performance of the models is compared with Mean Squared Error (MSE), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The study results show that there is no single model that consistently outperforms others for all cryptocurrencies. Models such as XGBoost and Random Forests show consistent and strong performance across different cryptocurrencies, proving their robustness in this particular use case. Deep learning algorithms, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs) and Long Short Term Memory Networks (LSTMs), show significant accuracy in predicting some cryptocurrencies.
S. Deepak, Preeti Gulia, Nasib Singh Gill, Mohammad Yahya · 7 authors
Internet of Things (IoT) plays an essential contribution in connecting devices and enabling seamless data exchange, leading to increased efficiency and convenience. However, security concerns in IoT systems are significant, as compromised devices can lead to data breaches and privacy violations. Blockchain technology can enhance IoT security by providing decentralized consensus, immutability, and transparent transaction records, ensuring secure and trustworthy communication and data integrity. This review article gives a succinct but thorough understanding of blockchain technology, covering architecture of blockchain, working principles, types, applications, platforms, and its role in the IoT environment. The study highlights potential benefits of blockchain like enhanced security and privacy, and explores its integration with IoT. Additionally, the study discusses various real-world applications, examines blockchain platforms, and addresses the limitations and challenges associated with blockchain technology. This review serves as a valuable resource for researchers and practitioners seeking a deeper understanding of blockchain’s potential and its implications in the IoT landscape.
By 2025, the Internet of Things (IoT) infrastructure is projected to encompass over 75 billion devices, facilitated by the increasing proliferation of intelligent applications. The Internet of Things ecosystem consists of sensors that function as data generators and applications that necessitate financial transactions to compensate the data producers. Security is a highly important concern. Employing blockchain technology makes it feasible to enhance security by maintaining payments in a ledger that is not just secure but also translucent, distributed, and immutable. This article provides an introductory overview of the Internet of Things (IoT) and subsequently delves into the many security threats and vulnerabilities arising within the IoT framework. This study provided an overview of the blockchain, focusing on its categorization and important properties. Moreover, this article examines the necessity of combining blockchain technology with the Internet of Things (IoT), in addition to reviewing relevant literature and the studies conducted by other scholars. This article offers insight into the uses of blockchain on the Internet of Things (IoT).
This study investigates the Fear & Greed Index, an indicator designed to reflect market sentiment regarding Bitcoin price, intending to utilize it as a predictive parameter for future price fluctuations. Due to the substantial volatility in Bitcoin prices and its significant influence on prediction outcomes, the dataset was preprocessed through monthly filtering and normalization. To forecast Bitcoin prices, an array of machine learning algorithms, including linear regression, random forest, and XGBoost, as well as their enhanced counterparts, were employed. The optimal model was identified by comparing the Grid Search XGBoost analysis results. This research holds implications for accurately predicting Bitcoin prices and underscores the impact of market sentiment on its valuation.