Yaroslav Meshcheryakov, Anna Melman, Oleg Evsutin, Vladimir Morozov · 5 authors
Cyber-physical systems and the Internet of things (IoT) are becoming an integral part of the digital society. The use of IoT services improves human life in many ways. Protection against cyber threats is an utmost important prospect of IoT devices operation. Malicious activities lead to confidential data leakage and incorrect performance of devices becomes critical. Therefore, development of effective solutions that can protect both IoT devices data and data exchange networks turns in to a real challenge. This study provides a critical analysis of the feasibility of using blockchain technology to protect constrained IoT devices data, justifies the choice of Practical Byzantine Fault Tolerance (PBFT) consensus algorithm for implementation on such devices, and simulates the main distributed ledger scenarios using PBFT. In this paper we investigate typical IoT network scenarios that can disrupt system performance. To ensure the adequacy of the models under study, we have analyzed the characteristics of real constrained IoT devices in terms of computing power and data rate. The simulation results demonstrate efficiency of the blockchain technology for constrained devices and make it possible to evaluate applicability limits of the chosen consensus algorithm.
Nishant Jagannath, Tudor Barbulescu, Karam M. Sallam, Ibrahim Elgendi · 8 authors
The Ethereum blockchain generates a significant amount of data due to its intrinsic transparency and decentralized nature. It is also referred to as on-chain data and is openly accessible to the world. Moreover, the on-chain data is timestamped, integrated, and validated into an open ledger. This important blockchain feature enables us to assess the network’s health and usage. It serves as a massive data warehouse for complex prediction algorithms that can effectively detect systemic trends and forecast future behavior. We adopt a quantitative approach using a subset of these metrics to determine the network’s true monetary value by developing a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) with the metrics most closely associated with the price as inputs. Since several hyperparameters regulate the learning process in an RNN, they are highly sensitive to their values. It is thus critical, to select optimal hyperparameters so that the training is quick and effective. Determining the optimal parameters of an RNN model is a tedious and complex process. Hence, previous studies have developed several self-adaptive approaches to determine the optimal values for various parameters effectively. However, none of the prior studies explore self-adaptive algorithms in deep learning models in conjunction with on-chain data to predict cryptocurrency prices. In this paper, we propose three self-adaptive techniques, each of which converges on a set of optimal parameters to predict the price of Ethereum accurately. We compare our results to a traditional LSTM model. Our approach exhibits 86.94% accuracy while maintaining a minimum error rate.
In this paper, we provide detailed analyses of the Bitcoin network and its main participants. We build a novel database using a large number of public and proprietary sources to link Bitcoin addresses to real entities and develop an extensive suite of algorithms to extract information about the behavior of the main market participants. We conduct three major pieces of analysis of the Bitcoin eco-system. First, we analyze the transaction volume and network structure of the main participants on the blockchain. Second, we document the concentration and regional composition of the miners which are the backbone of the verification protocol and ensure the integrity of the blockchain ledger. Finally, we analyze the ownership concentration of the largest holders of Bitcoin.
Internet of Things (IoT) consists of smart Things with evolution of ubiquitous computing. Fog Computing (FC) processes and analyzes data of these sensors near to users. However, the ever-increasing in number of Things and the consequent explosion in data traffic have led to fail traditional solutions of centralized storage. Blockchain is a new technology developed as a shared ledger build around peer-to-peer network to produce unchangeable blocks that contain multiple data. These blocks are linked to previous ones in sequence called chain through hash functions. Participants in blockchain selects a leader through one of consensus algorithms who adds new blocks in the chain to prevent dishonest nodes from creating invalid blocks. In this paper, we propose IoT based blockchain architecture named blockchain of Things to store medical records in a distributed manner. The architecture is emulated on Fog server Linux-based using Node.js and Postman. Three consensus protocols, namely: Proof of Work (PoW), Proof of Stake (PoS), and Byzantine Fault Tolerance (PBFT) are emulated and communicated using WebSocket. The consensus algorithms are evaluated in terms of CPU utilization and memory usage. The results show that PoS compared to PoW and PBFT is more lightweight and beneficial to IoT application.
Financial institutions such as banks regularly forecast the amount of finances an individual will have in his/her account in the near future. This can help banks in categorizing their customers so that banks can recommend financial products that matches the needs of their customers. In this work, we explored the historical financial transactions for predicting the amount a customer will receive through his/her transacting partners at a specific time. In particular, we use the Bitcoin transactional dataset, which has two main characteristics: i) network, and ii) temporal. This paper contributes by exploiting a specific kind of Graph Neural Network approach called Temporal-Graph Convolutional Network (T-GCN) for predicting the amount of Bitcoins received by a customer at a particular timestamp. The lower errors obtained using T-GCN approach compared to 11 baseline approaches (such as Support Vector Regression (SVR), Random Forest Regression (RFR), Vector Auto-Regressive (VAR), Long Short-Term Memory (LSTM), etc.) clearly demonstrate the effectiveness of T-GCN approach. In addition, our findings reveal that time is an important feature for such kind of predictive tasks.
Salim Lahmiri, Raafat George Saadé, Danielle Morin, Fassil Nebebe
Cryptocurrencies are digital assets gaining popularity and generating huge transactions on electronic platforms. We develop an ensemble predictive system based on artificial neural networks to forecast Bitcoin daily trading volume level. Indeed, although ensemble forecasts are increasingly employed in various forecasting tasks, developing an intelligent predictive system for Bitcoin trading volume based on ensemble forecasts has not been addressed yet. Ensemble Bitcoin trading volume are forecasted using two specific artificial neural networks; namely, radial basis function neural networks (RBFNN) and generalized regression neural networks (GRNN). They are adopted to respectively capture local and general patterns in Bitcoin trading volume data. Finally, the feedforward artificial neural network (FFNN) is implemented to generate Bitcoin final trading volume after having aggregated the forecasts from RBFNN and GRNN. In this regard, FFNN is executed to merge local and global forecasts in a nonlinear framework. Overall, our proposed ensemble predictive system reduced the forecasting errors by 18.81% and 62.86% when compared to its components RBFNN and GRNN, respectively. In addition, the ensemble system reduced the forecasting error by 90.49% when compared to a single FFNN used as a basic reference model. Thus, the empirical outcomes show that our proposed ensemble predictive model allows achieving an improvement in terms of forecasting. Regarding the practical results of this work, while being fast, applying the artificial neural networks to develop an ensemble predictive system to forecast Bitcoin daily trading volume is recommended to apply for addressing simultaneously local and global patterns used to characterize Bitcoin trading data. We conclude that the proposed artificial neural networks ensemble forecasting model is easy to implement and efficient for Bitcoin daily volume forecasting.
Blockchain is a decentralized database, which can protect the safety of trade and avoid double payment. Due to the widespread attention of researchers, the studies of this field have increased sharply in recent years. It is meaningful to reveal the development level and trends based on this literature. This paper adopts bibliometric methods to study the collaboration characteristics from the levels of author, institution and country. Furthermore, several kinds of collaboration networks and their centrality analysis are also presented, which not only display the development level and collaboration degree but also the evolution of author collaboration modes in different phases.
The promise and potential of blockchain to drive social impact is enormous. Blockchain will touch every significant industry which people interact with in dayto-day life. Blockchain will enable solutions that are not previously possible. Health sector recently attracted more initiatives than any other industry. Applications for blockchain in health include digital health records exchange and pharmaceutical supply chain management. In many of these areas, blockchain offers a more secure, decentralized and efficient solution than would otherwise be possible. Blockchain and machine learning (ML) technologies are gaining strong momentum and thrust around the world. Blockchain, a disruptive technology, made its big splash with crypto currencies invention and trading. On the other hand, with predictive and descriptive algorithms, ML is making considerable waves in harnessing existing data to identify patterns and gain insights. Congregating the two technologies can only make them super disruptive! Both have the potential to hasten data exploration and analysis as well as intensify transactions security. Additionally, distributed blockchains can be a significant and proven input for ML, which requires big datasets to make quality predictions. It goes without saying that each technology has its degree of complexity, but both artificial intelligence (AI) and blockchain are in situations where they can benefit from each other and help one another. Both these technologies are able to effect and enact upon data in different ways as their combination makes sense, which can take the exploitation of data to new levels. At the same time, the integration of ML and AI into the blockchain, and vice versa, can enhance blockchain's underlying architecture and boost AI's potential. Additionally, blockchain can also make AI more coherent and understandable for tracing and decision-making using ML techniques. Blockchain and its ledger can record all data and variables that go through a decision made under ML. The present chapter focuses on a few standard ML algorithms that are useful in supporting blockchain technology.
A Chatbot is a popular platform to enable users to interact with a software or website to gather information or execute actions in an automated fashion. In recent years, chatbots are being used for executing financial transactions, however, there are a number of security issues, such as secure authentication, data integrity, system availability and transparency, that must be carefully handled for their wide-scale adoption. Recently, the blockchain technology, with a number of security advantages, has emerged as one of the foundational technologies with the potential to disrupt a number of application domains, particularly in the financial sector. In this paper, we forward the idea of integrating a chatbot with blockchain technology in the view to improve the security issues in financial chatbots. More specifically, we present BONIK, a blockchain empowered chatbot for financial transactions, and discuss its architecture and design choices. Furthermore, we explore the developed Proof-of-Concept (PoC), evaluate its performance, analyse how different security and privacy issues are mitigated using BONIK.
Mahdi Alkaeed, Zaid Alamro, Muhammed Al-Ali, Hasan Abbas Al-Mohammed · 5 authors
Nowadays cryptography and their technologies have been with us for a long time. This field of science is developing day by day. Blockchain has come a long way since the birth of its first application. This application is Bitcoin which depends on Blockchain or DLT (Distributed Ledger Technology). Bitcoin is the most famous cryptocurrency intended for mass which appeared the first time in 2008. This innovation led to sparked in the digital revolution, which provides for many sectors and industries the security features, decentralization, and a reliable mechanism for transmission and storing data. This new technology led to the meteoric rise of Bitcoin and other such cryptocurrencies, so this has aroused the interest of governments and emerging companies to get an effective role in competition. We can apply blockchain in different sectors and different Internet of things (IoT). Cryptocurrency mining has become a major concern for computer professionals and also for those who earn more money from an additional source. Mining is a process for settle mathematical issues that depend on the strength and speed of the devices to solve those problems, which by resolving them leads to getting rewards in the form of a digital currency. In this paper, we will highlight the benefits of using both CPU (Central Processing Unit) and GPU (Graphical Processing Unit) and a practical comparison between them to find out the best and fastest based on previous studies and on the characteristics and architecture of each.
Xi He, Zhang Fan, Shenwen Lin, Mao Hongliang · 5 authors
Bitcoin is a decentralized cryptocurrency that has led to a new trading model. It allows people to trade directly without going through financial institutions such as banks. This model results in many transactions that occur outside the law and beyond ethical constraints. In such an anonymous environment, the large number of entities using Bitcoin, and the huge scale of the Bitcoin trading network make it difficult for users to have a rough idea of the entire trading network before transaction. Thus, it is of great theoretical and practical significance to summarize the research problems, achievements and possible research trends based on Bitcoin data analysis. Therefore, in this paper we review the literatures about data analysis on Bitcoin transaction entities. Starting from the relevant conceptual framework of Bitcoin, this paper divides the existing research models into three categories, heuristic algorithm identification of entities, transaction descriptive statistics and network analysis, and visual system analysis. By analyzing the transaction entity, Bitcoin transaction data can be processed in a manner which is similar to an account, such as a bank or credit card, thereby achieving the purpose of in-depth analysis of all transaction activities related to the account entity. Finally, we summarize the data analysis results of Bitcoin transaction network and prospects of the future research directions.
Blockchain is an innovative technology that can be used for processing and sharing data in a safe manner, via an unreliable network. This paper starts with a background of blockchains. We give some principal concepts of this new technology. Then we deal with machine learning as intelligent techniques that may be used for analyzing huge datasets and detecting eventual malicious transactions that can be occured in the untrusted network. We show the importance of such intelligent techniques when combining together to make good decisions in banking and finance. Our idea is applied to the Bitcoin system where the public Elliptic dataset from Kaggle is used as a benchmark. Since the latter is not all labeled, we use the k-means algorithm to partition the unlabeled data into two main clusters while the labeled data are moved to their corresponding clusters. Then, four machine learning techniques are used to classify all the data. The proposed system shows promising results in particular when combining k-means with the random forest classifier.
Juan Carlos López-Pimentel, Omar Rojas, Raúl Monroy
Even though there are researchers focused on implementing blockchain in auditing aspects, some data is cumbersome, and storing it on a blockchain requires too much computational cost. That's where a hybrid solution would be better. We aim to provide a blockchain-off-chain mechanism in the supply chain area. This paper presents an audit mechanism that, in the first instance, saves all the events (records) of a supply chain within a blockchain in a hashed form. In a second instance, users of a supply chain system can query integrity, data provenance, and traceability to blockchain through an intermediate server that establishes communication between blockchain and the supply chain. Our proposal has been validated employing a proof of concept where, some avocado supply chain services have been implemented using a microservices architecture.
Abstract In this work, the issue of predicting the edge weight in Bitcoin network has been addressed by leveraging community structure that involves members who trust with each other in their transactions. The proposed model consists of two main stages; the first one is the detection of trusted Bitcoin communities by implementing Newman- Girvan algorithm. In the context, the attributes of node have been modeling in different ways to get different structure of communities each time. Secondly, prediction the missing edge weight based on the neighbors of edge-source in community. In other words, the trust values that pointed to edge-target by neighbors are averaged to represent the prediction of missing edge weight. Practically, the model has been evaluated using two real-world datasets; Bitcoin-OTC and Bitcoin-Alpha datasets. The experimental results explicate the effectiveness of the proposed model comparable with other methods, where the minimization percentage for Bitcoin-OTC dataset is 4% and 18% for all and partial edges respectively. As for Bitcoin-Alpha dataset are 0% and 30% for all and partial edges respectively.
Flash Loan, as an emerging service in the decentralized finance ecosystem, allows users to request a non-collateral loan. While providing convenience, it also enables attackers to launch malicious operations with a large amount of asset that they do not have. Though there exist spot media reports of attacks that leverage Flash Loan, there lacks a comprehensive understanding of existing Flash Loan services. In this work, we take the first step to study the Flash Loan service provided by three popular platforms. Specifically, we first illustrate the interactions between Flash Loan providers and users. Then, we design three patterns to identify Flash Loan transactions. Based on the patterns, 76, 303 transactions are determined. The evaluation results show that the Flash Loan services get more popular over time. At last, we present four Flash Loan applications with real-world examples and propose two potential research directions.
In recent years, bitcoin has become a very attractive investment in financial industry, which is not controlled by governments, but is based on trust between transfers under the technology of block chain. Hence, forecasting future bitcoin cryptocurrency values is a problem that has attracted the attention of many researchers in the field, while proving to be a very challenging problem. This work presents an experimental analysis using LSTM and GRUs for forecasting bitcoin values in a minute-granulated time for the entire next day. To this end we also present our methodology for conducting the experiments. The final goal is to create the core of a financial prediction tool around the RNNs. In our experiments, we achieved interesting results such as a SMAPE of 0.0002, a RMSE of US$ 3.844 and a rRMSE of 0.0028 in a day where bitcoin rates vary from US$ 13.2K and US$ 14.6K, surpassing the results of SMAPE found in the literature and proposed limit of SMAPE smaller than 0.007 for forecasts.
Various ways have been done by researchers from all over the world to predict the price of Bitcoin which is the first digital commodity based on blockchain. Various forecasting and computational techniques have been widely applied and continue to be refined to find a prediction package that has the closest accuracy. The purpose of this research is to test hundreds of API data shared by hundreds of Cryptocurrency Markets and as a result we have succeeded in extracting the latest bitcoin price data from 20 Crypto Markets via shared APIs. This data will then be stored in a MySQL database on hosting automatically when a condition is reached. This data can then be mined continuously using Cronjob, and to facilitate the reading of data that has been collected, we use a telegram bot as well as using a web-based application. This step is expected to help in efforts to monitor bitcoin price movements and predict future price movements.
Srinidhi Srinivasan, Rubasri Sundar, Sam Joy Herald Immanuel, Ramesh Belvadi · 5 authors
The emergence of cryptocurrency has sparked an interesting debate on the future of financial transactions. Post-COVID, there will be unbelievable advancements in the most popular and promising technology, cryptocurrency particularly bitcoins, as it is more valuable than any form of cryptocurrencies. Our work is about bitcoin price alert system using bolt Internet of Things (IOT) and Blockchain. In this research paper, we will be writing a python program that checks the current price of the bitcoin and sends an alert if the current price of the bitcoin is higher than the set selling price. The program checks the current price of bitcoins whenever the price of bitcoins is updated. And at that same time it compares the current price with the bitcoin price that has been set as selling price. It alerts through buzzer, email and message. For this we use Bolt Internet of Things (IOT) module and ubuntu software for writing program in python.
Yue Wu, Liangtu Song, Lei Liu, Jincheng Li · 6 authors
Applying blockchain technology to the Internet of Things (IoT) remains a huge challenge. To meet the actual needs of IoT, a lightweight and high-throughput consensus mechanism, combined with blockchain technology, is proposed in this study. Blockchain nodes use the Diffie–Hellman algorithm for key negotiation. Sensors and blockchain nodes can use the shared key to generate HMAC (Hash-based Message Authentication Code) signatures for sensor-aware transactions and use the Verifiable Random Function to implement block nodes. Offline fast election, which is the node that wins the election, becomes the block node. Machine learning methods are also introduced to identify or remove outliers in the sensor data before such data are uploaded to the chain. Experimental results show that the system throughput synchronously increases as the test load increases. Moreover, when the test load is 800 tps, the system throughput reaches the maximum, close to 600 tps. When the test load exceeds 800 tps, the actual system throughput starts to drop, and approximately 90% of transactions have a delay time within 5000 ms. This method can be used in a lightweight IoT system.
Blockchain technologies have been very effective in processing distributed transactions securely. They have many applications including in handling bitcoin cryptocurrencies and smart contracts. More recently the use of blockchain has been explored for data science applications. This paper examines blockchain technologies and discusses their applications in data science and cyber security.
Abstract The paper deals with the architecture and design of the complex distributed classifier for the intelligent video surveillance systems considering the contemporary tendency to detect the abnormal or suspicious behavior of the individuals by means of behavioral features set analysis. This paper focuses on the implementation of multiagent systems concept and the distributed ledger technology to the distributed message board architecture. Two selected approaches to the distributed ledger implementation are analyzed and estimated in terms of classifiers cooperation. Some simulation results are provided and discussed in terms of time consumption.
Advancements in Artificial Intelligence (AI) and Big Data technologies are reshaping the global economy. The community currency network is receiving more attention through enhancing social ties within a community. As the most popular type of community currency, Time Banking (TB) is a generalized community exchange economy, which uses the time to evaluate each participant's contributions on the same scale rather than any equivalence with the official national currency. TB is a noble idea with the potential to improve the quality of life through prosocial, reciprocally beneficial activities among community members. However, it also brings new concerns about security and trust issues. Inspired by blockchain and smart contract, this paper introduces a Blockchain Integrated Timebanking (BIT) system to secure a decentralized community exchange economy. In BIT system, service providers and recipients can securely exchange effort through a self-executing smart contract without relying on a third-party trust authority. The blockchain network ensures immutability, auditability, and traceability of all data and service transactions recorded on the distributed ledger. A proof-of-concept prototype was implemented and tested on a private Ethereum network. The experimental results verify the feasibility of the proposed BIT to provide decentralized community service exchanges with limited computation overhead and network latency.
This paper describes the Distributed Ledger Network Analyzer (DiLeNA), a new software tool for the analysis of the transactions network recorded in Distributed Ledger Technologies (DLTs). The set of transactions in a DLT forms a complex network. Studying its characteristics and peculiarities is of paramount importance, in order to understand how users interact in the distributed ledger system. The tool design and implementation is introduced and some results are provided. In particular, the Bitcoin and Ethereum blockchains, i.e. the most famous and used DLTs at the time of writing, have been analyzed and compared.
Prediction of stock market trends is considered as an important task and is of great attention as predicting stock prices successfully may lead to attractive profits by making proper decisions. Stock market prediction is a major challenge owing to non-stationary, blaring, and chaotic data and thus, the prediction becomes challenging among the investors to invest the money for making profits. Initially, the blockchain network is fed to the blockchain network bridge from which the bitcoin data is acquired that is followed with the bitcoin prediction. Bitcoin prediction is performed using the proposed FuzzyCSA-based Deep Long short-term memory (LSTM). At first, the flow strength indicators are extracted based on Double exponential moving average (DEMA), Rate of Change (ROCR), Average True Range (ATR), Simple Moving Average (SMA), and Moving Average Convergence Divergence (MACD) from the blockchain data. Based on the extracted features, the prediction is done using FuzzyCSA-based Deep LSTM, which is the combination of FuzzyCSA with Deep LSTM. Then, the CSA is modified using the fuzzy operator for determining the optimal weights in Deep LSTM. The experimentation of the proposed method is performed from the openly available dataset. The analysis of the method in terms of Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) reveals that the proposed FuzzyCSA-based Deep LSTM acquired a minimal MAE of 0.4811, and the minimal RMSE of 0.3905, respectively.